Using An Artificial Intelligence Technique to Optimize Calcium Phosphates Synthesis Conditions

Size: px
Start display at page:

Download "Using An Artificial Intelligence Technique to Optimize Calcium Phosphates Synthesis Conditions"

Transcription

1 Using An Artificial Intelligence echnique to Optimize Calcium Phosphates Synthesis Conditions Mitra Asadi-Eydivand Department of Computer Engineering and Information echnology, Amirkabir University of echnology ehran, Iran Abstract he most widely used calcium phosphatebased bioceramic is biphasic calcium phosphate (BCP) consist of hydroxyapatite and tricalciumphosophate. Bioactivity and biodegradation of BCP is controlled by varying HA/CP ratio. In this study, a biphasic calcium phosphate composite (HA/b-CP) was synthesized through a wet chemical method. he structure and the composition of the resulting powders were characterized by different analytical techniques. o estimate and predict the synthesis conditions, a back-propagation neural network (BPNN) which has 2 inputs and 1 output was designed. Some experimental samples have been prepared to train the BPNN to get it to estimate the output parameters. hen BPNN is tested using some samples that have not been used in the training stage. o prepare the training and testing data sets, some experiments were performed. he effects of the ph of reactants and the Ca:P ratios of reactants, as input parameters, have been investigated on the Ca:P ratio of products, as output parameters. he comparison of the predicted values and the experimental data indicates that the developed model has an acceptable performance to estimate the Ca:P ratio of products in HA/beta-CP composite powder. Keywords- Artificial Neural Network; Biphasic Calcium Phosphate; Hydroxyapatite; ricalcium Phosphate; Synthesis I. INRODUCION Calcium phosphate-based ceramics have been very popular implanted materials for biological applications during past decades due to their similarity to human bone, biocompatibility and directly bone bonding. he most widely used calcium phosphates are hydroxyapatite (HA) and betatricalcium phosphate (b-cp) [1-2].With the development of computer technology and artificial intelligence theory, optimization of process parameters based on Artificial Neural Network (ANN) are designed in order to discover the proper condition to generate ideal biphasic calcium phosphates[1-4]. Insomuch as the experimental methods are time-consuming and expensive, computational models such Amir Hossein Hakami Vala/ Arghavan Farzadi/ Soheila Ali Akbari Ghavimi/ Mehran Solati-Hashjin Nanobiomaterials Laboratory (NBML), Biomedical Engineering Faculty Amirkabir University of echnology ehran, Iran as artificial neural networks (ANN) have been used for minimizing these deficiencies via estimating the results. ANN is a flexible mathematical structure which is capable of identifying complex nonlinear relationships between input and output data sets. ANN models have been found useful and efficient, particularly in problems for which the characteristics of the processes are difficult to describe using physical equations [5]. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation. he objective of this study is providing a back-propagation trained artificial neural network, which has 2 inputs and 1 output. Some data obtained from synthesizing of (HA/b- CP) composite were used to train the artificial neural network (ANN). o predict the proper synthesis condition of biphasic calcium phosphate, including hydroxyapatite and tricalcium phosphate the influence of input parameters, the ph and the initial Ca/P ratio of reactants, on output parameters, Ca/P ratio of products, have been investigated. II. MAERIALS AND MEHODS A. Synthesis and Characterization of Powders Calcium nitrate tetrahydrate with the chemical formula of Ca(NO 3 ) 2.4H 2 O and diammonium hydrogen phosphate with the formula of (NH4)2HPO4 were used as starting materials and sources of Ca and P respectively. HNO3ANDNH4OH WERE USED O ADJUS HE PH OF HE SOLUION mixture during the process. o prepare BCP powders by wet chemical method, diammonium hydrogen phosphate solution was added drop wise the calcium nitrate tetrahydrate solution under stirring conditions. he suspension was centrifuged and calcined at 1100 C. he chemical composition (Ca, and P contents) was determined by inductively coupled plasma (ICP) atomic emission spectroscopy using an ICP (AES ARL 3410) spectrometer. he effects of the initial Ca/P molar ratio and the ph of the solution on the composition of the precipitates are given in able I.

2 ABLE I.HE CONDIION FOR PREPARAION OF CALCIUM PHOSPHAE POWDERS A 20 C ph of Reactants Ca:P Ratio ( Reaction Products) Ca/P =1 Ca/P =1.5 Ca/P =1.67 Ca/P =2 Reactants In order to verify the performance of network, four extra samples were prepared and characterized by XRD and FIR. Phase analyses of powders were determined by X-ray diffraction (Philips PW 3710). he XRD data were collected over 2θ range of using Cu-Kα radiation ( mm). Phase identification was achieved by comparing the diffraction patterns of samples with ICDD (JCPDS) standards. Fourier transform infrared spectroscopy (Bruker IFS 48) using pellets of powdered samples mixed with KBr was performed to evaluate the functional groups of specimens. he FIR spectra were obtained over the region cm -1. B. Neural Network In this Study, the Neural Network oolbox software from Matlab has been used. hree back-propagation networks with three layers in each one with 5,10,50 neurons and hyperbolic tangent sigmoid transfer functions in hidden layer were designed. he network will be trained with the Levenberg-Marquardt back-propagation algorithm (trainlm). he Levenberg-Marquardt algorithm was designed to approach second-order training speed without having to compute the Hessian matrix[6]. he Levenberg-Marquardt algorithm was designed to approach second-order training speed without having to compute the Hessian matrix. When the performance function has the form of a sum of squares (as is typical in training feed forward networks), then the Hessian matrix can be approximated as equation (1): H = J J (1) And the gradient can be calculated as equation (2): g = J e (2) J is the Jacobian matrix that contains first derivatives of the network errors with respect to the weights and biases, and e is a vector of network errors. he Jacobian matrix can be computed by a standard back propagation technique that is much less complicated than computing the Hessian matrix. he Levenberg-Marquardt algorithm uses this approximation instead of the Hessian matrix in the equation (3): x 1 = xk [ J J µ I] k + + When the scalar µ is zero, this equation turns to be Newton's method, using the approximate Hessian matrix. When µ is large, the equation becomes gradient descent with a small step size. Newton's method is faster and more accurate near an error minimum, so the aim is to shift toward Newton's method as fast as possible. herefore, µ is decreased after each successful step (reduction in performance function) and is increased only when a trial step would increase the performance function. In this way, the performance function is always reduced at each iteration of the algorithm. In the other words, the training process continues until the validation error cannot be decreased anymore [7, 8]. he training process ran for each set of data shown in able I. he inputs and target data set were randomly divided into three sets as follows, he samples that were used for training the network that fit connection weights. he samples that were used for validation, measure network generalization; if the generalization stops improving, the training is terminated. he samples that had been used for testing were used as a completely independent test of network generalization. [9] In this paper, 41 samples were used for training, 3 samples for generalization and 8 samples for testing. he difference between three designed networks is between their number of hidden layer sneurons /n (n=5, 10, 50) means these three networks with n neurons in hidden layer. III. 1 J e RESULS AND DISCUSSION he Fig. 1 displays the network's outputs with respect to target for training, validation and test sets. Vertical axis is the output, and horizontal axis is the target. For a perfect fit, the data should fall along the 45-degree line where the network outputs are equal to the targets. According to Fig (1-a), that amount of slop in the all three processes of training, validation and test is and Y-intercepts is 0.13 that indicates less difference between targets and outputs. In Fig (1-b) the network which has 15 neurons in its hidden layer, the slope is nearer to line Y=X and the amount is shows better prediction than previous network. he slope of the line fitted to data points of network with 50 neurons in its hidden layer is that shows less accuracy in (3)

3 prediction, Fig (1-c). So, between three networks with 5, 10 and 50 neurons in hidden layer, the second one has the highest accuracy in prediction. 0432). In addition, the intensity of the HA peaks increases from BCP1 to BCP2 and BCP3 to BCP4 indicating that the amount of β-cp decreases as the amount of the ph of suspension is increased during the preparation procedure (at constant Ca/P ratio). (a) Figure 1(a-c). Neural networks regression plots a: /5, b: /10, c: /50 he FIR spectra of BCP powders is shown in Fig 3. he spectra illustrates the hydroxyl bond stretch at 3550 cm -1 and -2 HOP 4 at 970 cm -1 corresponding to HA and β-cp structure respectively. he vibrational bands of the phosphate ions are observed in all the samples. As there is an insignificant amount of hydroxyapatite in BCP3 and BCP4 samples, the hydroxyl band disappears and forms a relatively broad-band stretch over the range of cm -1 due to the adsorbed molecules of water. By increasing the amount of tricalcium phosphate phases in BCP2, BCP3 and BCP4 samples, the hydroxyl band at 633 cm -1 reduces in peak area. he hydroxyl vibrational band disappears in BCP1 sample. (c) According to able II, for four extra samples, the peaks of these samples were indexed according to standard patterns (JCPDS). he diffractograms of the samples BCP2 and BCP3 show additional peaks rather than the HA peaks. he peaks were identified to be corresponding to β-cp and indexed according to the standard card (JCPDS ). he intensity of the additional peaks increases from BCP2 to BCP3 indicating that the amount of β-cp decreases as the excess amount of the Ca/P ratio of reactants is increased during the preparation procedure (at constant ph). he sample BCP1 shows peaks of β-cp. his indicates that single phase β-cp was successfully synthesized at temperatures 1100 C [10]. he XRD pattern of BCP4 in Fig. 2 shows well-characterized peaks of pure, and the peaks were indexed according to the standard pattern (JCPDS 09- (b) BCP1 BCP2 BCP3 BCP4 ABLE II. HE EXPERIMENAL DAA OF FOUR BCP POWDERS Sample β-cp β-cp-riched-bcp HA-riched-BCP HA Initial Ca/P ratio ph Aging time For investigation of network accuracy, 4 extra data were run by the networks, and the predicted results were close to the experimental results. For these 4 supplementary data, the

4 network with 10 neurons in its hidden layer has the highest accuracy. (b) Figure 2. XRD patterns of BCP sample Figure3. FIR patterns of BCP samples According to Fig 4., the slope of the regression lines of network 5,10,50 neurons in its hidden layer were 1, 0.99, and 0.90 respectively. So far, prediction of product Ca/P using a network with ten neurons is proposed. (a) (c) Figure 4(a-c). Neural networks regression plots for four extra data a: 413-8/5, b: /10, c: /50 IV. CONCLUSION Biphasic calcium phosphate synthesis condition can be predicted by an ANN approach using the initial Ca/P ratio and ph as inputs and reactants Ca/P ratio as output. By changing the configuration of network, the amount of error can be optimized for having the best prediction. Levenberg-Marquardt back propagation algorithm was designed in which the neural network with 50 neurons has the maximum errors in predicting the reactant Ca/P ratios due to over-fitting caused by using too many neurons in the hidden layer. he ANN with 10 neurons in hidden layer has minimum errors in predicting Ca/P ratio of products, and fewer numbers of neurons can decrease the time it takes to train the network. his well-trained ANN with 10 neurons is expected to be very helpful and powerful for predicting the biphasic calcium phosphate synthesis condition.

5 REFERENCES [1] A. Farzadi,M. Solati-Hashjin, F. Bakhshi, A. Aminian, Synthesis and characterization of hydroxyapatite/ β -tricalcium phosphate nanocomposites using microwave irradiation, Ceramics International, Vol. 37, pp. 65 7, 2011 [2] S. J. Kalita, A. Bhardwaj, H. A. Bhatt, Nanocrystalline calcium phosphate ceramics in biomedical engineering, Materials Science and Engineering C, Vol. 27, pp , [3]. V. hamaraiselvi, S. Rajeswari, Biological evaluation of bioceramic materials A Review, rends Biomater. Artif. Organs, Vol.18, pp. 9-17, [4] I. Mobasherpour, M. Solati-Hashjin, A. Kazemzadeh, Synthesis of nanocrystalline hydroxyapatite by using precipitation method, Journal of Alloys and Compounds, Vol. 430, pp , [5] M. Paliwal and U.A. Kumar, Neural networks and statistical techniques: A review of applications. Expert Systems with Applications, 36 (2009) [6] I. Mukherjee, S. Routroy, Comparing the performance of neural networks deeloped by using Levenberg- Marquardt and Quasi- Newton with the gradient descent algorithm for modelling a multiple response grinding process, Exper Systems with Application, 39 (2012) [7] M.A. Costa, A.P. Braga, B. R. Menezes, Improving generalization of MLPs with sliding mode control and the Levenberg Marquardt algorithm, Neurocomputing, 70 (2007) [8] M.A. Costa, A.P. Braga, B. R. Menezes, Improving generalization of MLPs with sliding mode control and the Levenberg Marquardt algorithm, Neurocomputing, Vol. 70, pp , [9] Abraham, A., 129: Artificial Neural Networks. Handbook of Measuring System Design, PH Sydenham and R. horn, eds. John Wiley & Sons, [10] A. Esin, N. Mahmutyazıcıoğlu, S. Altıntaş, Drying and sintering of ceramic based parts using microwave heating, Key Engineering Materials, Vol. 264, pp , 2004

EFFECT OF TEMPERATURE ON SYNTHESIS OF HYDROXYAPATITE FROM LIMESTONE

EFFECT OF TEMPERATURE ON SYNTHESIS OF HYDROXYAPATITE FROM LIMESTONE Estd. 2008 Vol. 8 No.1 133-137 January - March 2015 ISSN: 0974-1496 e-issn: 0976-0083 CODEN: RJCABP http://www.rasayanjournal.com http://www.rasayanjournal.co.in EFFECT OF TEMPERATURE ON SYNTHESIS OF HYDROXYAPATITE

More information

Synthesis and Characterization of Hydroxyapatite Nanocrystals via Chemical Precipitation Technique

Synthesis and Characterization of Hydroxyapatite Nanocrystals via Chemical Precipitation Technique R Iranian Journal of Pharmaceutical Sciences SPring 2008: 4(2): 127-134 www.ijps.ir Original Article Synthesis and Characterization of Hydroxyapatite Nanocrystals via Chemical Precipitation Technique Hossein

More information

Facile Synthesis and Catalytic Properties of CeO 2 with Tunable Morphologies from Thermal Transformation of Cerium Benzendicarboxylate Complexes

Facile Synthesis and Catalytic Properties of CeO 2 with Tunable Morphologies from Thermal Transformation of Cerium Benzendicarboxylate Complexes Electronic Supplementary Information Facile Synthesis and Catalytic Properties of CeO 2 with Tunable Morphologies from Thermal Transformation of Cerium Benzendicarboxylate Complexes Yuhua Zheng, Kai Liu,

More information

Artificial Neural Networks (ANN) Xiaogang Su, Ph.D. Department of Mathematical Science University of Texas at El Paso

Artificial Neural Networks (ANN) Xiaogang Su, Ph.D. Department of Mathematical Science University of Texas at El Paso Artificial Neural Networks (ANN) Xiaogang Su, Ph.D. Department of Mathematical Science University of Texas at El Paso xsu@utep.edu Fall, 2018 Outline Introduction A Brief History ANN Architecture Terminology

More information

ESTIMATION OF HOURLY MEAN AMBIENT TEMPERATURES WITH ARTIFICIAL NEURAL NETWORKS 1. INTRODUCTION

ESTIMATION OF HOURLY MEAN AMBIENT TEMPERATURES WITH ARTIFICIAL NEURAL NETWORKS 1. INTRODUCTION Mathematical and Computational Applications, Vol. 11, No. 3, pp. 215-224, 2006. Association for Scientific Research ESTIMATION OF HOURLY MEAN AMBIENT TEMPERATURES WITH ARTIFICIAL NEURAL NETWORKS Ömer Altan

More information

Effect of Surfactant in Formation of Hydroxyapatite Nano-Rods under Hydrothermal Conditions

Effect of Surfactant in Formation of Hydroxyapatite Nano-Rods under Hydrothermal Conditions R Iranian Journal of Pharmaceutical Sciences Spring 2008: 4(2): 157-162 www.ijps.ir Original Article Effect of Surfactant in Formation of Hydroxyapatite Nano-Rods under Hydrothermal Conditions Mehrnaz

More information

Synthesis of Biphasic Calcium Phosphate and its Behaviour in Simulated Body Fluid

Synthesis of Biphasic Calcium Phosphate and its Behaviour in Simulated Body Fluid ASEAN J. Sci. Technol. Dev., 33(2): 63 68 Synthesis of Biphasic Calcium Phosphate and its Behaviour in Simulated Body Fluid X. V. BÙI 1,2 AND T. D. THẮNG 1 The main goal of this study is to elaborate and

More information

International Journal of Scientific & Engineering Research, Volume 5, Issue 3, March-2014 ISSN

International Journal of Scientific & Engineering Research, Volume 5, Issue 3, March-2014 ISSN 156 Copper Nanoparticles: Green Synthesis Characterization Y.Suresh*1, S.Annapurna*2, G.Bhikshamaiah*3, A.K.Singh#4 Abstract Present work describes the synthesis nanoparticles using papaya extract as a

More information

Synthesis and Characterization of Porous Silica Gels for Biomedical Applications

Synthesis and Characterization of Porous Silica Gels for Biomedical Applications Trends Biomater. Artif. Organs, Vol 18 (2), January 2005 http://www.sbaoi.org Synthesis and Characterization of Porous Silica Gels for Biomedical Applications U. Vijayalakshmi, A. Balamurugan and S. Rajeswari

More information

The Effect of Additives on Characteristics of Hydroxyapatite Particles Produced in Flame Reactor

The Effect of Additives on Characteristics of Hydroxyapatite Particles Produced in Flame Reactor The Effect of Additives on Characteristics of Hydroxyapatite Particles Produced in Flame Reactor Widiyastuti a*, Kusdianto a, Agung Nugroho a, Hakun Wira a, Sugeng Winardi a, and Kikuo Okuyama b a Department

More information

Forecasting of Rain Fall in Mirzapur District, Uttar Pradesh, India Using Feed-Forward Artificial Neural Network

Forecasting of Rain Fall in Mirzapur District, Uttar Pradesh, India Using Feed-Forward Artificial Neural Network International Journal of Engineering Science Invention ISSN (Online): 2319 6734, ISSN (Print): 2319 6726 Volume 2 Issue 8ǁ August. 2013 ǁ PP.87-93 Forecasting of Rain Fall in Mirzapur District, Uttar Pradesh,

More information

Synthesis and characterization of nano-hydroxyapatite (n-hap) using the wet chemical technique

Synthesis and characterization of nano-hydroxyapatite (n-hap) using the wet chemical technique Vol. 8(32), pp. 1639-1645, 30 August, 2013 DOI: 10.5897/IJPS2013.3990 ISSN 1992-1950 2013 Academic Journals http://www.academicjournals.org/ijps International Journal of Physical Sciences Full Length Research

More information

Electronic Supplementary Information for MS:

Electronic Supplementary Information for MS: Electronic Supplementary Material (ESI) for RSC Advances. This journal is The Royal Society of Chemistry 2014 Electronic Supplementary Information for MS: Solid State Structural Transformation of Bromide

More information

Wind Power Forecasting using Artificial Neural Networks

Wind Power Forecasting using Artificial Neural Networks Wind Power Forecasting using Artificial Neural Networks This paper aims at predicting the power output of wind turbines using artificial neural networks,two different algorithms and models were trained

More information

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD

ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD WHAT IS A NEURAL NETWORK? The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided

More information

PREPARATION OF SILICON DOPED HYDROXYAPATITE

PREPARATION OF SILICON DOPED HYDROXYAPATITE PREPARATION OF SILICON DOPED HYDROXYAPATITE Klaudia Paljar, Sebastijan Orlić, Emilija Tkalčec, Hrvoje Ivanković Faculty of Chemical Engineering and Technology, University of Zagreb HR-10001 Zagreb, Marulićev

More information

Journal of Faculty of Engineering & Technology SYNTHESIS AND CHARACTERIZATION OF CALCIUM DEFICIENT HYDROXYAPATITE NANOCRYSTALS

Journal of Faculty of Engineering & Technology SYNTHESIS AND CHARACTERIZATION OF CALCIUM DEFICIENT HYDROXYAPATITE NANOCRYSTALS PAK BULLET TRAIN (PBT) JFET 23(2) (2016) 101-109 Journal of Faculty of Engineering & Technology journal homepage: www.pu.edu.pk/journals/index.php/jfet/index SYNTHESIS AND CHARACTERIZATION OF CALCIUM DEFICIENT

More information

An artificial neural networks (ANNs) model is a functional abstraction of the

An artificial neural networks (ANNs) model is a functional abstraction of the CHAPER 3 3. Introduction An artificial neural networs (ANNs) model is a functional abstraction of the biological neural structures of the central nervous system. hey are composed of many simple and highly

More information

Ethylenediaminetetraacetic Acid-Assisted Synthesis of Nano Antimony Oxide by Microwave Method

Ethylenediaminetetraacetic Acid-Assisted Synthesis of Nano Antimony Oxide by Microwave Method Ethylenediaminetetraacetic Acid-Assisted Synthesis of Nano Antimony Oxide by Microwave Method Azadeh Tadjarodi*, Mohammad karimpour Department of Chemistry, Iran University of Science and Technology, Narmak,

More information

Supplementary Information for Self-assembled, monodispersed, flowerlike γ-alooh

Supplementary Information for Self-assembled, monodispersed, flowerlike γ-alooh Supplementary Information for Self-assembled, monodispersed, flowerlike γ-alooh hierarchical superstructures for greatly fast removal of heavy metal ions with high efficiency Yong-Xing Zhang, a,b Yong

More information

Efficient Co-Fe layered double hydroxide photocatalysts for water oxidation under visible light

Efficient Co-Fe layered double hydroxide photocatalysts for water oxidation under visible light Supplementary Information Efficient Co-Fe layered double hydroxide photocatalysts for water oxidation under visible light Sang Jun Kim, a Yeob Lee, a Dong Ki Lee, a Jung Woo Lee a and Jeung Ku Kang* a,b

More information

Supporting Information for: Emulsion-assisted synthesis of monodisperse binary metal nanoparticles

Supporting Information for: Emulsion-assisted synthesis of monodisperse binary metal nanoparticles Supporting Information for: Emulsion-assisted synthesis of monodisperse binary metal nanoparticles Zhen Yin, Ding Ma* and Xinhe Bao* Synthesis of the PdCu nanoparticles: All synthesis was carried out under

More information

Efficient dead time correction of G-M counters using feed forward artificial neural network

Efficient dead time correction of G-M counters using feed forward artificial neural network NUKLEONIKA 2013;58(2):317 321 ORIGINAL PAPER Efficient dead time correction of G-M counters using feed forward artificial neural network Masoomeh Arkani, Hossein Khalafi, Mohammad Arkani Abstract. Dead

More information

Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks

Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks Int. J. of Thermal & Environmental Engineering Volume 14, No. 2 (2017) 103-108 Prediction of Hourly Solar Radiation in Amman-Jordan by Using Artificial Neural Networks M. A. Hamdan a*, E. Abdelhafez b

More information

driving agent and study of photocatalytic activity Mohammad Salehi Department of Chemistry, Iran University of Science and Technology, Narmak, Tehran

driving agent and study of photocatalytic activity Mohammad Salehi Department of Chemistry, Iran University of Science and Technology, Narmak, Tehran A simplified microwave-assisted synthesis of NiMoO 4 nanoparticles by using organic driving agent and study of photocatalytic activity Azadeh Tadjarodi *, Raheleh Pradehkhorram, Mina Imani, Samaneh Ebrahimi,

More information

Sub-10-nm Au-Pt-Pd Alloy Trimetallic Nanoparticles with. High Oxidation-Resistant Property as Efficient and Durable

Sub-10-nm Au-Pt-Pd Alloy Trimetallic Nanoparticles with. High Oxidation-Resistant Property as Efficient and Durable Electronic Supplementary Material (ESI) for ChemComm. This journal is The Royal Society of Chemistry 2014 Electronic Supplementary Information Sub-10-nm Au-Pt-Pd Alloy Trimetallic Nanoparticles with High

More information

Research Article Prediction of Materials Density according to Number of Scattered Gamma Photons Using Optimum Artificial Neural Network

Research Article Prediction of Materials Density according to Number of Scattered Gamma Photons Using Optimum Artificial Neural Network Computational Methods in Physics, Article ID 0, pages http://dx.doi.org/0./0/0 Research Article Prediction of Materials Density according to Number of Scattered Gamma Photons Using Optimum Artificial Neural

More information

Address for Correspondence

Address for Correspondence Research Article APPLICATION OF ARTIFICIAL NEURAL NETWORK FOR INTERFERENCE STUDIES OF LOW-RISE BUILDINGS 1 Narayan K*, 2 Gairola A Address for Correspondence 1 Associate Professor, Department of Civil

More information

Synthesis of nano-sized anatase TiO 2 with reactive {001} facets using lamellar protonated titanate as precursor

Synthesis of nano-sized anatase TiO 2 with reactive {001} facets using lamellar protonated titanate as precursor Supporting Information Synthesis of nano-sized anatase TiO 2 with reactive {001} facets using lamellar protonated titanate as precursor Liuan Gu, Jingyu Wang *, Hao Cheng, Yunchen Du and Xijiang Han* Department

More information

Synthesis of 2 ) Structures by Small Molecule-Assisted Nucleation for Plasmon-Enhanced Photocatalytic Activity

Synthesis of 2 ) Structures by Small Molecule-Assisted Nucleation for Plasmon-Enhanced Photocatalytic Activity Electronic Supplementary Material (ESI) for ChemComm. This journal is The Royal Society of Chemistry 2015 Electronic Supplementary Information Synthesis of Au@UiO-66(NH 2 ) Structures by Small Molecule-Assisted

More information

(IJIRSE) International Journal of Innovative Research in Science & Engineering ISSN (Online)

(IJIRSE) International Journal of Innovative Research in Science & Engineering ISSN (Online) Synthesis, Size Characterization and Photocatalytic Activities of Zinc Ferrites and Cobalt Ferrites Nanoparticles Using Oxidative Degradations of Methylene Blue, Crystal Violet and Alizarin Red s in Aqueous

More information

Available online Research Article. Hamideh Saravani* and Mehdi Sanjarani V.

Available online   Research Article. Hamideh Saravani* and Mehdi Sanjarani V. Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2016, 8(4):1408-1413 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Synthesis and characterization of Cu 2 BaO 4 nanoparticles

More information

Synthesis gas production via the biogas reforming reaction over Ni/MgO-Al 2 O 3 and Ni/CaO-Al 2 O 3 catalysts

Synthesis gas production via the biogas reforming reaction over Ni/MgO-Al 2 O 3 and Ni/CaO-Al 2 O 3 catalysts Synthesis gas production via the biogas reforming reaction over Ni/MgO-Al 2 O 3 and Ni/CaO-Al 2 O 3 catalysts N.D. Charisiou 1,2, A. Baklavaridis 1, V.G. Papadakis 2, M.A. Goula 1 1 Department of Environmental

More information

Bandgap engineering through nanocrystalline magnetic alloy grafting on. graphene

Bandgap engineering through nanocrystalline magnetic alloy grafting on. graphene Electronic Supplementary Material (ESI) for Physical Chemistry Chemical Physics. This journal is the Owner Societies 2014 Electronic Supplementary Information (ESI) for Bandgap engineering through nanocrystalline

More information

Synthesis of Uniform Hollow Oxide Nanoparticles. through Nanoscale Acid Etching

Synthesis of Uniform Hollow Oxide Nanoparticles. through Nanoscale Acid Etching Supporting Information Synthesis of Uniform Hollow Oxide Nanoparticles through Nanoscale Acid Etching Kwangjin An, Soon Gu Kwon, Mihyun Park, Hyon Bin Na, Sung-Il Baik, Jung Ho Yu, Dokyoon Kim, Jae Sung

More information

Data Mining Part 5. Prediction

Data Mining Part 5. Prediction Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,

More information

Neural Networks (Part 1) Goals for the lecture

Neural Networks (Part 1) Goals for the lecture Neural Networks (Part ) Mark Craven and David Page Computer Sciences 760 Spring 208 www.biostat.wisc.edu/~craven/cs760/ Some of the slides in these lectures have been adapted/borrowed from materials developed

More information

PATTERN RECOGNITION FOR PARTIAL DISCHARGE DIAGNOSIS OF POWER TRANSFORMER

PATTERN RECOGNITION FOR PARTIAL DISCHARGE DIAGNOSIS OF POWER TRANSFORMER PATTERN RECOGNITION FOR PARTIAL DISCHARGE DIAGNOSIS OF POWER TRANSFORMER PO-HUNG CHEN 1, HUNG-CHENG CHEN 2, AN LIU 3, LI-MING CHEN 1 1 Department of Electrical Engineering, St. John s University, Taipei,

More information

Multilayer Perceptron

Multilayer Perceptron Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Single Perceptron 3 Boolean Function Learning 4

More information

Reading Group on Deep Learning Session 1

Reading Group on Deep Learning Session 1 Reading Group on Deep Learning Session 1 Stephane Lathuiliere & Pablo Mesejo 2 June 2016 1/31 Contents Introduction to Artificial Neural Networks to understand, and to be able to efficiently use, the popular

More information

Novel fungus-titanate bio-nano composites as high performance. absorbents for the efficient removal of radioactive ions from.

Novel fungus-titanate bio-nano composites as high performance. absorbents for the efficient removal of radioactive ions from. This journal is The Royal Society of Chemistry 0 Electronic Supplementary Information For Novel fungus-titanate bio-nano composites as high performance absorbents for the efficient removal of radioactive

More information

Vasil Khalidov & Miles Hansard. C.M. Bishop s PRML: Chapter 5; Neural Networks

Vasil Khalidov & Miles Hansard. C.M. Bishop s PRML: Chapter 5; Neural Networks C.M. Bishop s PRML: Chapter 5; Neural Networks Introduction The aim is, as before, to find useful decompositions of the target variable; t(x) = y(x, w) + ɛ(x) (3.7) t(x n ) and x n are the observations,

More information

Novel fluorescent matrix embedded carbon quantum dots enrouting stable gold and silver hydrosols

Novel fluorescent matrix embedded carbon quantum dots enrouting stable gold and silver hydrosols Novel fluorescent matrix embedded carbon quantum dots enrouting stable gold and silver hydrosols Shouvik Mitra a, Sourov Chandra b, Prasun Patra a, Panchanan Pramanik b *, Arunava Goswami a * a AERU, Biological

More information

RA P.1 (1-12) APT:m v 1.73 Prn:28/01/2008; 15:51 apt2439 by:laima p. 1. J. Manickaraj and N. Balasubramanian

RA P.1 (1-12) APT:m v 1.73 Prn:28/01/2008; 15:51 apt2439 by:laima p. 1. J. Manickaraj and N. Balasubramanian RA P.1 (1-12) APT:m v 1.73 Prn:28/01/2008; 15:51 apt2439 by:laima p. 1 Advanced Powder Technology 0 (2008) 1 12 www.brill.nl/apt Original paper Estimation of the Heat Transfer Coefficient in a Liquid Solid

More information

Comparative Application of Radial Basis Function and Multilayer Perceptron Neural Networks to Predict Traffic Noise Pollution in Tehran Roads

Comparative Application of Radial Basis Function and Multilayer Perceptron Neural Networks to Predict Traffic Noise Pollution in Tehran Roads Journal of Ecological Engineering Received: 2017.10.02 Accepted: 2017.10.28 Published: 2018.01.01 Volume 19, Issue 1, January 2018, pages 113 121 https://doi.org/10.12911/22998993/79411 Comparative Application

More information

Advanced Pharmaceutical Analysis

Advanced Pharmaceutical Analysis Lecture 2 Advanced Pharmaceutical Analysis IR spectroscopy Dr. Baraa Ramzi Infrared Spectroscopy It is a powerful tool for identifying pure organic and inorganic compounds. Every molecular compound has

More information

Supporting Information

Supporting Information Electronic Supplementary Material (ESI) for ChemComm. This journal is The Royal Society of Chemistry 2014 Supporting Information A Highly stable Metal- and Nitrogen-doped Nanocomposite derived from Zn/Ni-ZIF-8

More information

Lecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning

Lecture 10. Neural networks and optimization. Machine Learning and Data Mining November Nando de Freitas UBC. Nonlinear Supervised Learning Lecture 0 Neural networks and optimization Machine Learning and Data Mining November 2009 UBC Gradient Searching for a good solution can be interpreted as looking for a minimum of some error (loss) function

More information

A STATE-SPACE NEURAL NETWORK FOR MODELING DYNAMICAL NONLINEAR SYSTEMS

A STATE-SPACE NEURAL NETWORK FOR MODELING DYNAMICAL NONLINEAR SYSTEMS A STATE-SPACE NEURAL NETWORK FOR MODELING DYNAMICAL NONLINEAR SYSTEMS Karima Amoura Patrice Wira and Said Djennoune Laboratoire CCSP Université Mouloud Mammeri Tizi Ouzou Algeria Laboratoire MIPS Université

More information

Electrochemical Water Splitting by Layered and 3D Cross-linked Manganese Oxides: Correlating Structural Motifs and Catalytic Activity

Electrochemical Water Splitting by Layered and 3D Cross-linked Manganese Oxides: Correlating Structural Motifs and Catalytic Activity Electronic Supplementary Information Electrochemical Water Splitting by Layered and 3D Cross-linked Manganese Oxides: Correlating Structural Motifs and Catalytic Activity Arno Bergmann,* a Ivelina Zaharieva,*

More information

Electronic Supplementary Material. Methods. Synthesis of reference samples in Figure 1(b) Nano Res.

Electronic Supplementary Material. Methods. Synthesis of reference samples in Figure 1(b) Nano Res. Electronic Supplementary Material Shaped Pt Ni nanocrystals with an ultrathin Pt-enriched shell derived from one-pot hydrothermal synthesis as active electrocatalysts for oxygen reduction Jun Gu 1,, Guangxu

More information

Electronic Supporting Information

Electronic Supporting Information Electronic Supplementary Material (ESI) for ChemComm. This journal is The Royal Society of Chemistry 2015 Electronic Supporting Information for Mechanochemical reactions studied by in situ Raman spectroscopy:

More information

SYNTHESIS OF CADMIUM SULFIDE NANOSTRUCTURES BY NOVEL PRECURSOR

SYNTHESIS OF CADMIUM SULFIDE NANOSTRUCTURES BY NOVEL PRECURSOR Nanomaterials: Applications and Properties (NAP-2011). Vol. 1, Part I 107 SYNTHESIS OF CADMIUM SULFIDE NANOSTRUCTURES BY NOVEL PRECURSOR M. Salavati Niasari 1,2* 1 Department of Inorganic Chemistry, Faculty

More information

ECLT 5810 Classification Neural Networks. Reference: Data Mining: Concepts and Techniques By J. Hand, M. Kamber, and J. Pei, Morgan Kaufmann

ECLT 5810 Classification Neural Networks. Reference: Data Mining: Concepts and Techniques By J. Hand, M. Kamber, and J. Pei, Morgan Kaufmann ECLT 5810 Classification Neural Networks Reference: Data Mining: Concepts and Techniques By J. Hand, M. Kamber, and J. Pei, Morgan Kaufmann Neural Networks A neural network is a set of connected input/output

More information

Introduction Neural Networks - Architecture Network Training Small Example - ZIP Codes Summary. Neural Networks - I. Henrik I Christensen

Introduction Neural Networks - Architecture Network Training Small Example - ZIP Codes Summary. Neural Networks - I. Henrik I Christensen Neural Networks - I Henrik I Christensen Robotics & Intelligent Machines @ GT Georgia Institute of Technology, Atlanta, GA 30332-0280 hic@cc.gatech.edu Henrik I Christensen (RIM@GT) Neural Networks 1 /

More information

Multilayer Perceptron = FeedForward Neural Network

Multilayer Perceptron = FeedForward Neural Network Multilayer Perceptron = FeedForward Neural Networ History Definition Classification = feedforward operation Learning = bacpropagation = local optimization in the space of weights Pattern Classification

More information

Design Collocation Neural Network to Solve Singular Perturbed Problems with Initial Conditions

Design Collocation Neural Network to Solve Singular Perturbed Problems with Initial Conditions Article International Journal of Modern Engineering Sciences, 204, 3(): 29-38 International Journal of Modern Engineering Sciences Journal homepage:www.modernscientificpress.com/journals/ijmes.aspx ISSN:

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK DEVELOPMENT OF HYDROXYAPATITE NANOCEREMICS FOR METHANOL AND ETHANOL SENSOR RAJENDRA

More information

Synthesis of 12 nm iron oxide nanoparticles

Synthesis of 12 nm iron oxide nanoparticles Electronic Supporting Information for Dendronized iron oxide nanoparticles as contrast agent for MRI Brice Basly, a Delphine Felder-Flesch,* a Pascal Perriat, b Claire Billotey, c Jacqueline Taleb, c Geneviève

More information

RESULTS AND DISCUSSION Characterization of pure CaO and Zr-TiO 2 /CaO nanocomposite

RESULTS AND DISCUSSION Characterization of pure CaO and Zr-TiO 2 /CaO nanocomposite RESULTS AND DISCUSSION 4.1. Characterization of pure CaO and Zr-TiO 2 /CaO nanocomposite 4.1.1. Scanning electron microscopy analysis (SEM) SEM images of prepared CaO are shown in Fig. 4.1 (a and b). CaO

More information

Thunderstorm Forecasting by using Artificial Neural Network

Thunderstorm Forecasting by using Artificial Neural Network Thunderstorm Forecasting by using Artificial Neural Network N.F Nik Ismail, D. Johari, A.F Ali, Faculty of Electrical Engineering Universiti Teknologi MARA 40450 Shah Alam Malaysia nikfasdi@yahoo.com.my

More information

Solubility Modeling of Diamines in Supercritical Carbon Dioxide Using Artificial Neural Network

Solubility Modeling of Diamines in Supercritical Carbon Dioxide Using Artificial Neural Network Australian Journal of Basic and Applied Sciences, 5(8): 166-170, 2011 ISSN 1991-8178 Solubility Modeling of Diamines in Supercritical Carbon Dioxide Using Artificial Neural Network 1 Mehri Esfahanian,

More information

Synthesis of Polyhedral Phenylsilsesquioxanes with KF as the Source of Fluoride Ion

Synthesis of Polyhedral Phenylsilsesquioxanes with KF as the Source of Fluoride Ion Supporting information for: Synthesis of Polyhedral Phenylsilsesquioxanes with KF as the Source of Fluoride Ion Matjaž Koželj and Boris Orel* National Institute of Chemistry, Hajdrihova 19, SI-1000 Ljubljana,

More information

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis

Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.

More information

Having a High Mg/Al Molar Ratio

Having a High Mg/Al Molar Ratio SUPPORTING INFORMATION High-Temperature CO 2 Sorption on Hydrotalcite Having a High Mg/Al Molar Ratio Suji Kim, Sang Goo Jeon, and Ki Bong Lee*, Department of Chemical and Biological Engineering, Korea

More information

SYNTHESIS OF HA AND BETA-TCP USING SOL-GEL PROCESS AND ANALYSIS WITH FTIR

SYNTHESIS OF HA AND BETA-TCP USING SOL-GEL PROCESS AND ANALYSIS WITH FTIR SYNTHESIS OF HA AND BETA-TCP USING SOL-GEL PROCESS AND ANALYSIS WITH FTIR Leonardo Ribeiro Rodrigues, leo5002@fem.unicamp.br Carmen Gilda Barroso Tavares Dias, carmendias@fem.unicamp.br DEMA-FEM-UNICAMP

More information

Chapter 4 Neural Networks in System Identification

Chapter 4 Neural Networks in System Identification Chapter 4 Neural Networks in System Identification Gábor HORVÁTH Department of Measurement and Information Systems Budapest University of Technology and Economics Magyar tudósok körútja 2, 52 Budapest,

More information

Supporting Information

Supporting Information Electronic Supplementary Material (ESI) for Journal of Materials Chemistry C. This journal is The Royal Society of Chemistry 2018 Supporting Information A difunctional metal organic framework with Lewis

More information

Pattern Classification

Pattern Classification Pattern Classification All materials in these slides were taen from Pattern Classification (2nd ed) by R. O. Duda,, P. E. Hart and D. G. Stor, John Wiley & Sons, 2000 with the permission of the authors

More information

Shape-selective Synthesis and Facet-dependent Enhanced Electrocatalytic Activity and Durability of Monodisperse Sub-10 nm Pt-Pd Tetrahedrons and Cubes

Shape-selective Synthesis and Facet-dependent Enhanced Electrocatalytic Activity and Durability of Monodisperse Sub-10 nm Pt-Pd Tetrahedrons and Cubes Supporting Information Shape-selective Synthesis and Facet-dependent Enhanced Electrocatalytic Activity and Durability of Monodisperse Sub-10 nm Pt-Pd Tetrahedrons and Cubes An-Xiang Yin, Xiao-Quan Min,

More information

Portugaliae Electrochimica Acta 26/4 (2008)

Portugaliae Electrochimica Acta 26/4 (2008) Portugaliae Electrochimica Acta 6/4 (008) 6-68 PORTUGALIAE ELECTROCHIMICA ACTA Comparison of Regression Model and Artificial Neural Network Model for the Prediction of Volume Percent of Diamond Deposition

More information

Electronic Supplementary Information (ESI) Green synthesis of shape-defined anatase TiO 2 nanocrystals wholly exposed with {001} and {100} facets

Electronic Supplementary Information (ESI) Green synthesis of shape-defined anatase TiO 2 nanocrystals wholly exposed with {001} and {100} facets Electronic Supplementary Information (ESI) Green synthesis of shape-defined anatase TiO 2 nanocrystals wholly exposed with {001} and {100} facets Lan Wang, a Ling Zang, b Jincai Zhao c and Chuanyi Wang*

More information

Artificial Intelligence

Artificial Intelligence Artificial Intelligence Jeff Clune Assistant Professor Evolving Artificial Intelligence Laboratory Announcements Be making progress on your projects! Three Types of Learning Unsupervised Supervised Reinforcement

More information

Design Collocation Neural Network to Solve Singular Perturbation Problems for Partial Differential Equations

Design Collocation Neural Network to Solve Singular Perturbation Problems for Partial Differential Equations Design Collocation Neural Network to Solve Singular Perturbation Problems for Partial Differential Equations Abstract Khalid. M. Mohammed. Al-Abrahemee Department of Mathematics, College of Education,

More information

A Novel 2-D Model Approach for the Prediction of Hourly Solar Radiation

A Novel 2-D Model Approach for the Prediction of Hourly Solar Radiation A Novel 2-D Model Approach for the Prediction of Hourly Solar Radiation F Onur Hocao glu, Ö Nezih Gerek, and Mehmet Kurban Anadolu University, Dept of Electrical and Electronics Eng, Eskisehir, Turkey

More information

PREDICTION OF HEAT TRANSFER COEFFICIENTS BY ANN FOR ALUMINUM & STEEL MATERIAL

PREDICTION OF HEAT TRANSFER COEFFICIENTS BY ANN FOR ALUMINUM & STEEL MATERIAL PREDICION OF HEA RANSFER COEFFICIENS BY ANN FOR ALUMINUM & SEEL MAERIAL Ilker MER 1 1 Vocational School of Maritime, Mustafa Kemal University, Iskenderun, urkey imert@mku.edu.tr Hüseyin uran ARA 2 2 Engineering

More information

Computational statistics

Computational statistics Computational statistics Lecture 3: Neural networks Thierry Denœux 5 March, 2016 Neural networks A class of learning methods that was developed separately in different fields statistics and artificial

More information

Combination of M-Estimators and Neural Network Model to Analyze Inside/Outside Bark Tree Diameters

Combination of M-Estimators and Neural Network Model to Analyze Inside/Outside Bark Tree Diameters Combination of M-Estimators and Neural Network Model to Analyze Inside/Outside Bark Tree Diameters Kyriaki Kitikidou, Elias Milios, Lazaros Iliadis, and Minas Kaymakis Democritus University of Thrace,

More information

Machine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6

Machine Learning for Large-Scale Data Analysis and Decision Making A. Neural Networks Week #6 Machine Learning for Large-Scale Data Analysis and Decision Making 80-629-17A Neural Networks Week #6 Today Neural Networks A. Modeling B. Fitting C. Deep neural networks Today s material is (adapted)

More information

Supporting Information

Supporting Information Supporting Information A Low-Temperature Solid-Phase Method to Synthesize Highly Fluorescent Carbon Nitride Dots with Tunable Emission Juan Zhou, Yong Yang, and Chun-yang Zhang* Single-Molecule Detection

More information

A novel one-step synthesis of PEG passivated multicolour fluorescent carbon dots for potential biolabeling application

A novel one-step synthesis of PEG passivated multicolour fluorescent carbon dots for potential biolabeling application Supporting Information A novel one-step synthesis of PEG passivated multicolour fluorescent carbon dots for potential biolabeling application Abhay Sachdev, Ishita Matai, S. Uday Kumar, Bharat Bhushan,

More information

Artificial Neural Networks. Edward Gatt

Artificial Neural Networks. Edward Gatt Artificial Neural Networks Edward Gatt What are Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning Very

More information

All materials and reagents were obtained commercially and used without further

All materials and reagents were obtained commercially and used without further Reversible shrinkage and expansion of a blue photofluorescene cadmium coordination polymer and in situ tetrazole ligand synthesis Hong Deng,* a Yong-Cai Qiu, a Ying-Hua Li, a Zhi-Hui liu, a Rong-Hua Zeng,

More information

Supporting Information

Supporting Information Supporting Information Yb 3 O(OH) 6 Cl.2H 2 O An anion exchangeable hydroxide with a cationic inorganic framework structure Helen V. Goulding, a Sarah E. Hulse, a William Clegg, b Ross W. Harrington, b

More information

Keywords- Source coding, Huffman encoding, Artificial neural network, Multilayer perceptron, Backpropagation algorithm

Keywords- Source coding, Huffman encoding, Artificial neural network, Multilayer perceptron, Backpropagation algorithm Volume 4, Issue 5, May 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Huffman Encoding

More information

Artificial Neural Networks. MGS Lecture 2

Artificial Neural Networks. MGS Lecture 2 Artificial Neural Networks MGS 2018 - Lecture 2 OVERVIEW Biological Neural Networks Cell Topology: Input, Output, and Hidden Layers Functional description Cost functions Training ANNs Back-Propagation

More information

Supporting Information:

Supporting Information: Supporting Information: Columnar Self-assembly of Cu 2 S Hexagonal Nanoplates Induced by Tin (IV)-X Complex Inorganic Surface Ligand Xiaomin Li, Huaibin Shen, Jinzhong Niu, Sen Li, Yongguang Zhang, Hongzhe

More information

4. Multilayer Perceptrons

4. Multilayer Perceptrons 4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output

More information

One-pot Solvent-free Synthesis of Sodium Benzoate from the Oxidation of Benzyl Alcohol over Novel Efficient AuAg/TiO 2 Catalysts

One-pot Solvent-free Synthesis of Sodium Benzoate from the Oxidation of Benzyl Alcohol over Novel Efficient AuAg/TiO 2 Catalysts Electronic Supplementary Information One-pot Solvent-free Synthesis of Sodium Benzoate from the Oxidation of Benzyl Alcohol over Novel Efficient AuAg/TiO 2 Catalysts Ying Wang, Jia-Min Zheng, Kangnian

More information

Neural Networks Learning the network: Backprop , Fall 2018 Lecture 4

Neural Networks Learning the network: Backprop , Fall 2018 Lecture 4 Neural Networks Learning the network: Backprop 11-785, Fall 2018 Lecture 4 1 Recap: The MLP can represent any function The MLP can be constructed to represent anything But how do we construct it? 2 Recap:

More information

Neural Networks Lecture 4: Radial Bases Function Networks

Neural Networks Lecture 4: Radial Bases Function Networks Neural Networks Lecture 4: Radial Bases Function Networks H.A Talebi Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Winter 2011. A. Talebi, Farzaneh Abdollahi

More information

Growth of silver nanocrystals on graphene by simultaneous reduction of graphene oxide and silver ions with a rapid and efficient one-step approach

Growth of silver nanocrystals on graphene by simultaneous reduction of graphene oxide and silver ions with a rapid and efficient one-step approach Growth of silver nanocrystals on graphene by simultaneous reduction of graphene oxide and silver ions with a rapid and efficient one-step approach Xiu-Zhi Tang, a Zongwei Cao, b Hao-Bin Zhang, a Jing Liu

More information

ECE521 Lecture 7/8. Logistic Regression

ECE521 Lecture 7/8. Logistic Regression ECE521 Lecture 7/8 Logistic Regression Outline Logistic regression (Continue) A single neuron Learning neural networks Multi-class classification 2 Logistic regression The output of a logistic regression

More information

Multilayer Perceptrons and Backpropagation

Multilayer Perceptrons and Backpropagation Multilayer Perceptrons and Backpropagation Informatics 1 CG: Lecture 7 Chris Lucas School of Informatics University of Edinburgh January 31, 2017 (Slides adapted from Mirella Lapata s.) 1 / 33 Reading:

More information

CSC 578 Neural Networks and Deep Learning

CSC 578 Neural Networks and Deep Learning CSC 578 Neural Networks and Deep Learning Fall 2018/19 3. Improving Neural Networks (Some figures adapted from NNDL book) 1 Various Approaches to Improve Neural Networks 1. Cost functions Quadratic Cross

More information

Accelerated Sonochemical Synthesis of Calcium Deficient Hydroxyapatite Nanoparticles: Structural and Morphological Evolution

Accelerated Sonochemical Synthesis of Calcium Deficient Hydroxyapatite Nanoparticles: Structural and Morphological Evolution Copyright 201 American Scientific Publishers All rights reserved Printed in the United States of America Journal of Biomaterials and Tissue Engineering Vol., 295 299, 201 Accelerated Sonochemical Synthesis

More information

Mr. Harshit K. Dave 1, Dr. Keyur P. Desai 2, Dr. Harit K. Raval 3

Mr. Harshit K. Dave 1, Dr. Keyur P. Desai 2, Dr. Harit K. Raval 3 Investigations on Prediction of MRR and Surface Roughness on Electro Discharge Machine Using Regression Analysis and Artificial Neural Network Programming Mr. Harshit K. Dave 1, Dr. Keyur P. Desai 2, Dr.

More information

Urchin-like Ni-P microstructures: A facile synthesis, properties. and application in the fast removal of heavy-metal ions

Urchin-like Ni-P microstructures: A facile synthesis, properties. and application in the fast removal of heavy-metal ions SUPPORTING INFORMATION Urchin-like Ni-P microstructures: A facile synthesis, properties and application in the fast removal of heavy-metal ions Yonghong Ni *a, Kai Mi a, Chao Cheng a, Jun Xia a, Xiang

More information

Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011!

Artificial Neural Networks and Nonparametric Methods CMPSCI 383 Nov 17, 2011! Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011! 1 Todayʼs lecture" How the brain works (!)! Artificial neural networks! Perceptrons! Multilayer feed-forward networks! Error

More information

Supplementary Information

Supplementary Information Supplementary Information Stable aluminum metal-organic frameworks (Al-MOFs) for balanced CO 2 and water selectivity Haiwei Li, Xiao Feng, * Dou Ma, Mengxi Zhang, Yuanyuan Zhang, Yi Liu, Jinwei Zhang,

More information