A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers
|
|
|
- Jodie Willis
- 5 years ago
- Views:
Transcription
1 A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers Thomas E. Potok, Ph.D. Computational Data Analytics Group Oak Ridge National Laboratory ORNL is managed by UT-Battelle 1 for Computational the US Department Data Analytics of Energy
2 Motivation and Goals Scientific data is increasingly large and complex, making new discovery difficult Can deep learning and novel architectures provide a way of aiding scientific discovery? Each pixel represents a 512x512 matrix of values from Spallation Neutron Source at ORNL 2 Computational Data Analytics
3 Deep Learning Performance What could you do with HPC, Quantum Neuromorphic? 3 Computational Data Analytics
4 Motivations for novel architectures Deep Learning network topologies are layered due to computability Does a complex topology offer better results? Deep Learning Hyper-parameters are hard to tune Can a CNN be quickly tuned for a new scientific datasets? Deep Learning Trained models are hard to deploy Can models be deployed on or near scientific instruments? 4 Computational Data Analytics
5 Scientific Data Scientific Instrument Hypothesis Complex Topology Hardware Implementation Auto Tuned Hyper Parameters 5 Computational Data Analytics
6 Scientific Data Scientific Instrument Methods Complex Topology Hardware Implementation Auto Tuned Hyper Parameters 6 Computational Data Analytics
7 Rational Quantum HPC Neuromorphic Hints at speed up of certain hard problems Computational parallelization Native neural networks, very low power 7 Computational Data Analytics
8 Experimental Goals Quantum Test feasibility of complex topologies (intra-layer connections) USC Lockheed Martin Quantum Computation Center D-Wave HPC Test evolutionary algorithms to auto-tune hyperparameters ORNL s Titan Neuromorphic Test the ability to represent neural network models in low power hardware UTK Memristive Nida System 8 Computational Data Analytics
9 How do we compare the architectures? Boltzmann Machine Convolutional Neural Network Spiking Neural Network Quantum HPC Neuromorphic The MNIST database contains 60,000 training images and 10,000 testing images Very small images size, 28x Computational Data Analytics
10 Common Ground Quantum Physics Computer Science Electrical Engineering Neuroscience Entanglement Link Synapse Qubit Node Neuron Chimera Network 10 Computational Data Analytics
11 Limited Boltzmann Machine Network 10 Output Nodes (one for each digit) Fully-Connected (every node in output is connected to every node in hidden). One Layer Fully-Connected (every node in visible is connected to every node in hidden). 784 Visible Nodes (28x28 pixels for image) 11 Computational Data Analytics
12 Quantum Results USC/ISI D-Wave Complex topology learns and provides better results than no intra-layer connection Limited Boltzmann Machine learning from training examples Limited Boltzmann Machine more accurate than restricted BM 12 Computational Data Analytics
13 HPC Results 500 nodes on Titan Demonstrates an effective way of auto tuning a CNN 13 Computational Data Analytics
14 Neuromorphic ORNL/UT NIDA network on Memristor 20X more energy-efficient than their CMOS counterparts 14 Computational Data Analytics
15 Conclusion Complex topologies with intra-layer connects have better classification performance than without connections HPC can be used to auto-tune CNN topologies Neuromorphic hardware has the potential to implement deep learning network in very low-power hardware A first step towards richer DL on novel architectures 15 Computational Data Analytics
16 Next Step Evaluate the strengths and weaknesses of each approach Quantum: Explore more complex networks One Layer HPC: Auto tune on Limited Boltzmann machines model Neuromorphic: Implement of Limited Boltzmann on FPGA version of neuromorphic hardware 16 Computational Data Analytics
17 Team Deep Learning/HPC Robert Patton (ORNL) Steven Young (ORNL) Thomas Potok (PI/ORNL) Quantum Computing Federico Spedalieri (USC/ISI) Ke-Thia Yao(USC/ISI) Bob Lucas (USC/ISI) Jeremy Liu (USC) Neuromorphic Computing Garrett Rose (UT) Katie Schuman (ORNL) Gangotree Chakma (UT) Program Manager Robinson Pino (DOE ASCR) 17 Computational Data Analytics
18 Questions? 18 Computational Data Analytics
LOCKHEED MARTIN SITE UPDATE 11 APRIL 2018 MUNICH, GERMANY Kristen Pudenz Senior Quantum Applications Engineer
LOCKHEED MARTIN SITE UPDATE 11 APRIL 2018 MUNICH, GERMANY Kristen Pudenz Senior Quantum Applications Engineer THE USC-LM QUANTUM COMPUTING CENTER Dr. Edward H. Ned Allen Chief Scientist and LM Senior Fellow
UNSUPERVISED LEARNING
UNSUPERVISED LEARNING Topics Layer-wise (unsupervised) pre-training Restricted Boltzmann Machines Auto-encoders LAYER-WISE (UNSUPERVISED) PRE-TRAINING Breakthrough in 2006 Layer-wise (unsupervised) pre-training
Implementation of a Restricted Boltzmann Machine in a Spiking Neural Network
Implementation of a Restricted Boltzmann Machine in a Spiking Neural Network Srinjoy Das Department of Electrical and Computer Engineering University of California, San Diego srinjoyd@gmail.com Bruno Umbria
Neuromorphic computing with Memristive devices. NCM group
Neuromorphic computing with Memristive devices NCM group Why neuromorphic? New needs for computing Recognition, Mining, Synthesis (Intel) Increase of Fault (nanoscale engineering) SEMICONDUCTOR TECHNOLOGY
How to do backpropagation in a brain
How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto & Google Inc. Prelude I will start with three slides explaining a popular type of deep
Quantum Computing & Scientific Applications at ORNL
Quantum Computing & Scientific Applications at ORNL Pavel Lougovski Oak Ridge National Laboratory ORNL is managed by UT-Battelle for the US Department of Energy ORNL at a glance: DOE s largest science
Jakub Hajic Artificial Intelligence Seminar I
Jakub Hajic Artificial Intelligence Seminar I. 11. 11. 2014 Outline Key concepts Deep Belief Networks Convolutional Neural Networks A couple of questions Convolution Perceptron Feedforward Neural Network
Deep Learning Srihari. Deep Belief Nets. Sargur N. Srihari
Deep Belief Nets Sargur N. Srihari srihari@cedar.buffalo.edu Topics 1. Boltzmann machines 2. Restricted Boltzmann machines 3. Deep Belief Networks 4. Deep Boltzmann machines 5. Boltzmann machines for continuous
(Feed-Forward) Neural Networks Dr. Hajira Jabeen, Prof. Jens Lehmann
(Feed-Forward) Neural Networks 2016-12-06 Dr. Hajira Jabeen, Prof. Jens Lehmann Outline In the previous lectures we have learned about tensors and factorization methods. RESCAL is a bilinear model for
Introduction to (Convolutional) Neural Networks
Introduction to (Convolutional) Neural Networks Philipp Grohs Summer School DL and Vis, Sept 2018 Syllabus 1 Motivation and Definition 2 Universal Approximation 3 Backpropagation 4 Stochastic Gradient
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)
Knowledge Extraction from DBNs for Images
Knowledge Extraction from DBNs for Images Son N. Tran and Artur d Avila Garcez Department of Computer Science City University London Contents 1 Introduction 2 Knowledge Extraction from DBNs 3 Experimental
Building a Multi-FPGA Virtualized Restricted Boltzmann Machine Architecture Using Embedded MPI
Building a Multi-FPGA Virtualized Restricted Boltzmann Machine Architecture Using Embedded MPI Charles Lo and Paul Chow {locharl1, pc}@eecg.toronto.edu Department of Electrical and Computer Engineering
Deep Learning Architecture for Univariate Time Series Forecasting
CS229,Technical Report, 2014 Deep Learning Architecture for Univariate Time Series Forecasting Dmitry Vengertsev 1 Abstract This paper studies the problem of applying machine learning with deep architecture
Convolutional Neural Networks. Srikumar Ramalingam
Convolutional Neural Networks Srikumar Ramalingam Reference Many of the slides are prepared using the following resources: neuralnetworksanddeeplearning.com (mainly Chapter 6) http://cs231n.github.io/convolutional-networks/
Addressing Challenges in Neuromorphic Computing with Memristive Synapses
Addressing Challenges in Neuromorphic Computing with Memristive Synapses Vishal Saxena 1, Xinyu Wu 1 and Maria Mitkova 2 1 Analog Mixed-Signal and Photonic IC (AMPIC) Lab 2 Nanoionic Materials and Devices
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1
What Do Neural Networks Do? MLP Lecture 3 Multi-layer networks 1 Multi-layer networks Steve Renals Machine Learning Practical MLP Lecture 3 7 October 2015 MLP Lecture 3 Multi-layer networks 2 What Do Single
LOCKHEED MARTIN SITE UPDATE
LOCKHEED MARTIN SITE UPDATE 25 SEPTEMBER 2018 Julia Kwok Software Engineer Quantum Applications THE USC-LM QUANTUM COMPUTING CENTER Dr. Edward H. Ned Allen Chief Scientist and LM Senior Fellow Lockheed
How can ideas from quantum computing improve or speed up neuromorphic models of computation?
Neuromorphic Computation: Architectures, Models, Applications Associative Memory Models with Adiabatic Quantum Optimization Kathleen Hamilton, Alexander McCaskey, Jonathan Schrock, Neena Imam and Travis
Convolutional Neural Network Architecture
Convolutional Neural Network Architecture Zhisheng Zhong Feburary 2nd, 2018 Zhisheng Zhong Convolutional Neural Network Architecture Feburary 2nd, 2018 1 / 55 Outline 1 Introduction of Convolution Motivation
Restricted Boltzmann Machines
Restricted Boltzmann Machines http://deeplearning4.org/rbm-mnist-tutorial.html Slides from Hugo Larochelle, Geoffrey Hinton, and Yoshua Bengio CSC321: Intro to Machine Learning and Neural Networks, Winter
Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box
ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton Motivation Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses
Generalizing Convolutional Neural Networks to Graphstructured. Ben Walker Department of Mathematics, UNC-Chapel Hill 5/4/2018
Generalizing Convolutional Neural Networks to Graphstructured Data Ben Walker Department of Mathematics, UNC-Chapel Hill 5/4/2018 Overview Relational structure in data and how to approach it Defferrard,
De Novo molecular design with Deep Reinforcement Learning
De Novo molecular design with Deep Reinforcement Learning @olexandr Olexandr Isayev, Ph.D. University of North Carolina at Chapel Hill olexandr@unc.edu http://olexandrisayev.com About me Ph.D. in Chemistry
<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation)
Learning for Deep Neural Networks (Back-propagation) Outline Summary of Previous Standford Lecture Universal Approximation Theorem Inference vs Training Gradient Descent Back-Propagation
Modularity Matters: Learning Invariant Relational Reasoning Tasks
Summer Review 3 Modularity Matters: Learning Invariant Relational Reasoning Tasks Jason Jo 1, Vikas Verma 2, Yoshua Bengio 1 1: MILA, Universit de Montral 2: Department of Computer Science Aalto University,
Opportunities and challenges in near-term quantum computers
Opportunities and challenges in near-term quantum computers Alejandro Perdomo-Ortiz Senior Research Scientist, Quantum AI Lab. at NASA Ames Research Center and at the University Space Research Association,
Artificial Neural Networks. Introduction to Computational Neuroscience Tambet Matiisen
Artificial Neural Networks Introduction to Computational Neuroscience Tambet Matiisen 2.04.2018 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition
Spatial Transformer Networks
BIL722 - Deep Learning for Computer Vision Spatial Transformer Networks Max Jaderberg Andrew Zisserman Karen Simonyan Koray Kavukcuoglu Contents Introduction to Spatial Transformers Related Works Spatial
TYPES OF MODEL COMPRESSION. Soham Saha, MS by Research in CSE, CVIT, IIIT Hyderabad
TYPES OF MODEL COMPRESSION Soham Saha, MS by Research in CSE, CVIT, IIIT Hyderabad 1. Pruning 2. Quantization 3. Architectural Modifications PRUNING WHY PRUNING? Deep Neural Networks have redundant parameters.
Fast classification using sparsely active spiking networks. Hesham Mostafa Institute of neural computation, UCSD
Fast classification using sparsely active spiking networks Hesham Mostafa Institute of neural computation, UCSD Artificial networks vs. spiking networks backpropagation output layer Multi-layer networks
STDP Learning of Image Patches with Convolutional Spiking Neural Networks
STDP Learning of Image Patches with Convolutional Spiking Neural Networks Daniel J. Saunders, Hava T. Siegelmann, Robert Kozma College of Information and Computer Sciences University of Massachusetts Amherst
Speaker Representation and Verification Part II. by Vasileios Vasilakakis
Speaker Representation and Verification Part II by Vasileios Vasilakakis Outline -Approaches of Neural Networks in Speaker/Speech Recognition -Feed-Forward Neural Networks -Training with Back-propagation
LEADING THE EVOLUTION OF COMPUTE MARK KACHMAREK HPC STRATEGIC PLANNING MANAGER APRIL 17, 2018
LEADING THE EVOLUTION OF COMPUTE MARK KACHMAREK HPC STRATEGIC PLANNING MANAGER APRIL 17, 2018 INTEL S RESEARCH EFFORTS COMPONENTS RESEARCH INTEL LABS ENABLING MOORE S LAW DEVELOPING NOVEL INTEGRATION ENABLING
Neural Network Representation of Tensor Network and Chiral States
Neural Network Representation of Tensor Network and Chiral States Yichen Huang ( 黄溢辰 ) 1 and Joel E. Moore 2 1 Institute for Quantum Information and Matter California Institute of Technology 2 Department
Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers
Opportunities and challenges in quantum-enhanced machine learning in near-term quantum computers Alejandro Perdomo-Ortiz Senior Research Scientist, Quantum AI Lab. at NASA Ames Research Center and at the
Artificial Neural Networks D B M G. Data Base and Data Mining Group of Politecnico di Torino. Elena Baralis. Politecnico di Torino
Artificial Neural Networks Data Base and Data Mining Group of Politecnico di Torino Elena Baralis Politecnico di Torino Artificial Neural Networks Inspired to the structure of the human brain Neurons as
Topic 3: Neural Networks
CS 4850/6850: Introduction to Machine Learning Fall 2018 Topic 3: Neural Networks Instructor: Daniel L. Pimentel-Alarcón c Copyright 2018 3.1 Introduction Neural networks are arguably the main reason why
GPGPU ACCELERATED SIMULATION AND PARAMETER TUNING FOR NEUROMORPHIC APPLICATIONS
January 24, 2014 Parameter Tuning for Neuromorphic Applications 1 GPGPU ACCELERATED SIMULATION AND PARAMETER TUNING FOR NEUROMORPHIC APPLICATIONS Kris Carlson, Michael Beyeler, Nikil Dutt, Jeff Krichmar
Comparison of Modern Stochastic Optimization Algorithms
Comparison of Modern Stochastic Optimization Algorithms George Papamakarios December 214 Abstract Gradient-based optimization methods are popular in machine learning applications. In large-scale problems,
Bayesian Networks (Part I)
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Bayesian Networks (Part I) Graphical Model Readings: Murphy 10 10.2.1 Bishop 8.1,
Grundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Neural networks Daniel Hennes 21.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Logistic regression Neural networks Perceptron
Evolving Keras Architectures for Sensor Data Analysis
Evolving Keras Architectures for Sensor Data Analysis Petra Vidnerová Roman Neruda Institute of Computer Science The Czech Academy of Sciences FedCSIS 2017 Outline Introduction Deep Neural Networks KERAS
CSCI 315: Artificial Intelligence through Deep Learning
CSCI 35: Artificial Intelligence through Deep Learning W&L Fall Term 27 Prof. Levy Convolutional Networks http://wernerstudio.typepad.com/.a/6ad83549adb53ef53629ccf97c-5wi Convolution: Convolution is
Deep Learning (CNNs)
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Deep Learning (CNNs) Deep Learning Readings: Murphy 28 Bishop - - HTF - - Mitchell
A Video from Google DeepMind.
A Video from Google DeepMind http://www.nature.com/nature/journal/v518/n7540/fig_tab/nature14236_sv2.html Can machine learning teach us cluster updates? Lei Wang Institute of Physics, CAS https://wangleiphy.github.io
Spatial Transformation
Spatial Transformation Presented by Liqun Chen June 30, 2017 1 Overview 2 Spatial Transformer Networks 3 STN experiments 4 Recurrent Models of Visual Attention (RAM) 5 Recurrent Models of Visual Attention
The Origin of Deep Learning. Lili Mou Jan, 2015
The Origin of Deep Learning Lili Mou Jan, 2015 Acknowledgment Most of the materials come from G. E. Hinton s online course. Outline Introduction Preliminary Boltzmann Machines and RBMs Deep Belief Nets
IBM Systems for Cognitive Solutions
IBM Q Quantum Computing IBM Systems for Cognitive Solutions Ehningen 12 th of July 2017 Albert Frisch, PhD - albert.frisch@de.ibm.com 2017 IBM 1 st wave of Quantum Revolution lasers atomic clocks GPS sensors
Classification with Perceptrons. Reading:
Classification with Perceptrons Reading: Chapters 1-3 of Michael Nielsen's online book on neural networks covers the basics of perceptrons and multilayer neural networks We will cover material in Chapters
Regression Adjustment with Artificial Neural Networks
Regression Adjustment with Artificial Neural Networks Age of Big Data: data comes in a rate and in a variety of types that exceed our ability to analyse it Texts, image, speech, video Real motivation:
Convolutional Neural Networks
Convolutional Neural Networks Books» http://www.deeplearningbook.org/ Books http://neuralnetworksanddeeplearning.com/.org/ reviews» http://www.deeplearningbook.org/contents/linear_algebra.html» http://www.deeplearningbook.org/contents/prob.html»
REAL-TIME COMPUTING WITHOUT STABLE
REAL-TIME COMPUTING WITHOUT STABLE STATES: A NEW FRAMEWORK FOR NEURAL COMPUTATION BASED ON PERTURBATIONS Wolfgang Maass Thomas Natschlager Henry Markram Presented by Qiong Zhao April 28 th, 2010 OUTLINE
Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) For this week, Reading Chapter 4: Neural Networks (Mitchell, 1997) See Canvas For subsequent weeks: Scaling Learning Algorithms toward
Neural Networks, Computation Graphs. CMSC 470 Marine Carpuat
Neural Networks, Computation Graphs CMSC 470 Marine Carpuat Binary Classification with a Multi-layer Perceptron φ A = 1 φ site = 1 φ located = 1 φ Maizuru = 1 φ, = 2 φ in = 1 φ Kyoto = 1 φ priest = 0 φ
Probabilistic Models in Theoretical Neuroscience
Probabilistic Models in Theoretical Neuroscience visible unit Boltzmann machine semi-restricted Boltzmann machine restricted Boltzmann machine hidden unit Neural models of probabilistic sampling: introduction
RegML 2018 Class 8 Deep learning
RegML 2018 Class 8 Deep learning Lorenzo Rosasco UNIGE-MIT-IIT June 18, 2018 Supervised vs unsupervised learning? So far we have been thinking of learning schemes made in two steps f(x) = w, Φ(x) F, x
Deep Learning for NLP
Deep Learning for NLP Instructor: Wei Xu Ohio State University CSE 5525 Many slides from Greg Durrett Outline Motivation for neural networks Feedforward neural networks Applying feedforward neural networks
ECE521 Lectures 9 Fully Connected Neural Networks
ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance
A 68 Parallel Row Access Neuromorphic Core with 22K Multi-Level Synapses Based on Logic- Compatible Embedded Flash Memory Technology
A 68 Parallel Row Access Neuromorphic Core with 22K Multi-Level Synapses Based on Logic- Compatible Embedded Flash Memory Technology M. Kim 1, J. Kim 1, G. Park 1, L. Everson 1, H. Kim 1, S. Song 1,2,
Staying on the path Fred Rothganger
Staying on the path Fred Rothganger Sandia National Laboratories is a multi-mission laboratory managed and operated by Sandia Corporation, a wholly owned subsidiary of Lockheed Martin Corporation, for
Artificial Neural Networks
Artificial Neural Networks 鮑興國 Ph.D. National Taiwan University of Science and Technology Outline Perceptrons Gradient descent Multi-layer networks Backpropagation Hidden layer representations Examples
Mitosis Detection in Breast Cancer Histology Images with Multi Column Deep Neural Networks
Mitosis Detection in Breast Cancer Histology Images with Multi Column Deep Neural Networks IDSIA, Lugano, Switzerland dan.ciresan@gmail.com Dan C. Cireşan and Alessandro Giusti DNN for Visual Pattern Recognition
Introduction to Deep Learning
Introduction to Deep Learning Some slides and images are taken from: David Wolfe Corne Wikipedia Geoffrey A. Hinton https://www.macs.hw.ac.uk/~dwcorne/teaching/introdl.ppt Feedforward networks for function
CSE446: Neural Networks Spring Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer
CSE446: Neural Networks Spring 2017 Many slides are adapted from Carlos Guestrin and Luke Zettlemoyer Human Neurons Switching time ~ 0.001 second Number of neurons 10 10 Connections per neuron 10 4-5 Scene
Multivariate Methods in Statistical Data Analysis
Multivariate Methods in Statistical Data Analysis Web-Site: http://tmva.sourceforge.net/ See also: "TMVA - Toolkit for Multivariate Data Analysis, A. Hoecker, P. Speckmayer, J. Stelzer, J. Therhaag, E.
Learning to Disentangle Factors of Variation with Manifold Learning
Learning to Disentangle Factors of Variation with Manifold Learning Scott Reed Kihyuk Sohn Yuting Zhang Honglak Lee University of Michigan, Department of Electrical Engineering and Computer Science 08
A brain-inspired neuromorphic architecture for robust neural computation
A brain-inspired neuromorphic architecture for robust neural computation Fabio Stefanini and Giacomo Indiveri Institute of Neuroinformatics University of Zurich and ETH Zurich BIC Workshop @ ISCA40 June
Deep Neural Networks (1) Hidden layers; Back-propagation
Deep Neural Networs (1) Hidden layers; Bac-propagation Steve Renals Machine Learning Practical MLP Lecture 3 4 October 2017 / 9 October 2017 MLP Lecture 3 Deep Neural Networs (1) 1 Recap: Softmax single
Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning
Apprentissage, réseaux de neurones et modèles graphiques (RCP209) Neural Networks and Deep Learning Nicolas Thome Prenom.Nom@cnam.fr http://cedric.cnam.fr/vertigo/cours/ml2/ Département Informatique Conservatoire
Learning Deep Architectures for AI. Part II - Vijay Chakilam
Learning Deep Architectures for AI - Yoshua Bengio Part II - Vijay Chakilam Limitations of Perceptron x1 W, b 0,1 1,1 y x2 weight plane output =1 output =0 There is no value for W and b such that the model
Neural networks. Chapter 19, Sections 1 5 1
Neural networks Chapter 19, Sections 1 5 Chapter 19, Sections 1 5 1 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 19, Sections 1 5 2 Brains 10
Supervised Learning. George Konidaris
Supervised Learning George Konidaris gdk@cs.brown.edu Fall 2017 Machine Learning Subfield of AI concerned with learning from data. Broadly, using: Experience To Improve Performance On Some Task (Tom Mitchell,
Neuroevolution for sound event detection in real life audio: A pilot study
Neuroevolution for sound event detection in real life audio: A pilot study Christian Kroos & Mark D. Plumbley Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK Background
NEUROMORPHIC COMPUTING WITH MAGNETO-METALLIC NEURONS & SYNAPSES: PROSPECTS AND PERSPECTIVES
NEUROMORPHIC COMPUTING WITH MAGNETO-METALLIC NEURONS & SYNAPSES: PROSPECTS AND PERSPECTIVES KAUSHIK ROY ABHRONIL SENGUPTA, KARTHIK YOGENDRA, DELIANG FAN, SYED SARWAR, PRIYA PANDA, GOPAL SRINIVASAN, JASON
STA 414/2104: Lecture 8
STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable models Background PCA
Deep Learning with Coherent Nanophotonic Circuits
Yichen Shen, Nicholas Harris, Dirk Englund, Marin Soljacic Massachusetts Institute of Technology @ Berkeley, Oct. 2017 1 Neuromorphic Computing Biological Neural Networks Artificial Neural Networks 2 Artificial
SOLVING SPARSE REPRESENTATIONS FOR OBJECT CLASSIFICATION USING QUANTUM D-WAVE 2X MACHINE
SOLVING SPARSE REPRESENTATIONS FOR OBJECT CLASSIFICATION USING QUANTUM D-WAVE 2X MACHINE! Nga Nguyen, Amy Larson, Carleton Coffrin, John Perry, Gary Salazar, and Garrett Kenyon Los Alamos National Laboratory
CS 229 Project Final Report: Reinforcement Learning for Neural Network Architecture Category : Theory & Reinforcement Learning
CS 229 Project Final Report: Reinforcement Learning for Neural Network Architecture Category : Theory & Reinforcement Learning Lei Lei Ruoxuan Xiong December 16, 2017 1 Introduction Deep Neural Network
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks. Nicolas Le Roux and Yoshua Bengio Presented by Colin Graber
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks Nicolas Le Roux and Yoshua Bengio Presented by Colin Graber Introduction Representational abilities of functions with some
PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING
PREDICTION OF HETERODIMERIC PROTEIN COMPLEXES FROM PROTEIN-PROTEIN INTERACTION NETWORKS USING DEEP LEARNING Peiying (Colleen) Ruan, PhD, Deep Learning Solution Architect 3/26/2018 Background OUTLINE Method
CS 179: LECTURE 16 MODEL COMPLEXITY, REGULARIZATION, AND CONVOLUTIONAL NETS
CS 179: LECTURE 16 MODEL COMPLEXITY, REGULARIZATION, AND CONVOLUTIONAL NETS LAST TIME Intro to cudnn Deep neural nets using cublas and cudnn TODAY Building a better model for image classification Overfitting
Neural Networks. Mark van Rossum. January 15, School of Informatics, University of Edinburgh 1 / 28
1 / 28 Neural Networks Mark van Rossum School of Informatics, University of Edinburgh January 15, 2018 2 / 28 Goals: Understand how (recurrent) networks behave Find a way to teach networks to do a certain
Magnetic tunnel junction beyond memory from logic to neuromorphic computing WANJUN PARK DEPT. OF ELECTRONIC ENGINEERING, HANYANG UNIVERSITY
Magnetic tunnel junction beyond memory from logic to neuromorphic computing WANJUN PARK DEPT. OF ELECTRONIC ENGINEERING, HANYANG UNIVERSITY Magnetic Tunnel Junctions (MTJs) Structure High density memory
Dimensionality Reduction and Principle Components Analysis
Dimensionality Reduction and Principle Components Analysis 1 Outline What is dimensionality reduction? Principle Components Analysis (PCA) Example (Bishop, ch 12) PCA vs linear regression PCA as a mixture
PV021: Neural networks. Tomáš Brázdil
1 PV021: Neural networks Tomáš Brázdil 2 Course organization Course materials: Main: The lecture Neural Networks and Deep Learning by Michael Nielsen http://neuralnetworksanddeeplearning.com/ (Extremely
COMPLEX INPUT CONVOLUTIONAL NEURAL NETWORKS FOR WIDE ANGLE SAR ATR
COMPLEX INPUT CONVOLUTIONAL NEURAL NETWORKS FOR WIDE ANGLE SAR ATR Michael Wilmanski #*1, Chris Kreucher *2, & Alfred Hero #3 # University of Michigan 500 S State St, Ann Arbor, MI 48109 1 wilmansk@umich.edu,
Neutron inverse kinetics via Gaussian Processes
Neutron inverse kinetics via Gaussian Processes P. Picca Politecnico di Torino, Torino, Italy R. Furfaro University of Arizona, Tucson, Arizona Outline Introduction Review of inverse kinetics techniques
CS:4420 Artificial Intelligence
CS:4420 Artificial Intelligence Spring 2018 Neural Networks Cesare Tinelli The University of Iowa Copyright 2004 18, Cesare Tinelli and Stuart Russell a a These notes were originally developed by Stuart
Synaptic Devices and Neuron Circuits for Neuron-Inspired NanoElectronics
Synaptic Devices and Neuron Circuits for Neuron-Inspired NanoElectronics Byung-Gook Park Inter-university Semiconductor Research Center & Department of Electrical and Computer Engineering Seoul National
Feed-forward Network Functions
Feed-forward Network Functions Sargur Srihari Topics 1. Extension of linear models 2. Feed-forward Network Functions 3. Weight-space symmetries 2 Recap of Linear Models Linear Models for Regression, Classification
Deep learning quantum matter
Deep learning quantum matter Machine-learning approaches to the quantum many-body problem Joaquín E. Drut & Andrew C. Loheac University of North Carolina at Chapel Hill SAS, September 2018 Outline Why
Neural networks. Chapter 20, Section 5 1
Neural networks Chapter 20, Section 5 Chapter 20, Section 5 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 20, Section 5 2 Brains 0 neurons of
Few-shot learning with KRR
Few-shot learning with KRR Prudencio Tossou Groupe de Recherche en Apprentissage Automatique Départment d informatique et de génie logiciel Université Laval April 6, 2018 Prudencio Tossou (UL) Few-shot
Neural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA 1/ 21
Neural Networks Chapter 8, Section 7 TB Artificial Intelligence Slides from AIMA http://aima.cs.berkeley.edu / 2 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural
Neural Networks. Bishop PRML Ch. 5. Alireza Ghane. Feed-forward Networks Network Training Error Backpropagation Applications
Neural Networks Bishop PRML Ch. 5 Alireza Ghane Neural Networks Alireza Ghane / Greg Mori 1 Neural Networks Neural networks arise from attempts to model human/animal brains Many models, many claims of
Neural Networks with Applications to Vision and Language. Feedforward Networks. Marco Kuhlmann
Neural Networks with Applications to Vision and Language Feedforward Networks Marco Kuhlmann Feedforward networks Linear separability x 2 x 2 0 1 0 1 0 0 x 1 1 0 x 1 linearly separable not linearly separable
COSC 594 Final Presentation Membrane Systems/ P Systems
COSC 594 Final Presentation Membrane Systems/ P Systems Mesbah Uddin & Gangotree Chakma November, 6 Motivation of Unconventional Computing Parallel computing-- restricted in conventional computers Deterministic
Fundamentals of Computational Neuroscience 2e
Fundamentals of Computational Neuroscience 2e January 1, 2010 Chapter 10: The cognitive brain Hierarchical maps and attentive vision A. Ventral visual pathway B. Layered cortical maps Receptive field size
Neural Networks. David Rosenberg. July 26, New York University. David Rosenberg (New York University) DS-GA 1003 July 26, / 35
Neural Networks David Rosenberg New York University July 26, 2017 David Rosenberg (New York University) DS-GA 1003 July 26, 2017 1 / 35 Neural Networks Overview Objectives What are neural networks? How