Visual meta-learning for planning and control

Size: px
Start display at page:

Download "Visual meta-learning for planning and control"

Transcription

1 Visual meta-learning for planning and control Seminar on Current Works in Computer Chair of Pattern Recognition and Image Processing. Samuel Roth Winter Semester 2018/19 Albert-Ludwigs-Universität Freiburg

2 Content Motivation, Goal. Meta learning. Concept acquisition through meta learning (CAML). Implementation of CAML. Use observation classifier as reward functions. Experimental results. 1

3 Introduction - Motivation Motivation Reinforcement Learning needs rewards for learning. 2

4 Introduction - Motivation Example Tasks Motivation Reinforcement Learning needs rewards for learning. 2

5 Introduction - Motivation Example Tasks Motivation Reinforcement Learning needs rewards for learning. Specifying rewards are often hand crafted and domain specific. 2

6 Introduction - Motivation Example Tasks Motivation Reinforcement Learning needs rewards for learning. Specifying rewards are often hand crafted and domain specific. Learning rewards for a specific tasks requires large labeled dataset for training. 2

7 Introduction - Goal and Approach Goal Derive reward function. From camera input. Only few positive examples of success. Utilize information given by other tasks. 3

8 Introduction - Goal and Approach Goal Derive reward function. From camera input. Only few positive examples of success. Utilize information given by other tasks. Meta learning approach Learn to learn Train a model to classify tasks for multiple different tasks. Expect the model to learn internal representations. For a new task is given Model has a good initialization. 3

9 Introduction - Framework 4

10 Introduction - Framework 4

11 Meta Learning for few shot objective learning Concept Given a dataset of labeled observations over multiple tasks D i := {(o j, y j ) j = 1,, k; y j {0, 1}} A meta-learner f L and a classifier f C With the objective to f C = f L (D + new ; θ) : Observation [0, 1] min θ n i (o j,y j ) D train i L ( y j, f L (D + i ; θ)(o j ) ) 5

12 CAML - Concept Acquisition through meta learning. 6

13 CAML - Concept Acquisition through meta learning. Incorporate gradient descent for parameter adaption. 6

14 CAML - Concept Acquisition through meta learning. Incorporate gradient descent for parameter adaption. Adapt θ to new task τ: g(θ, D τ + ) := θ α θ L ( y i, f CAML (θ)(o i ) ) = θ τ (o i,y i ) D + τ 6

15 CAML - Concept Acquisition through meta learning. Incorporate gradient descent for parameter adaption. Adapt θ to new task τ: g(θ, D τ + ) := θ α θ L ( y i, f CAML (θ)(o i ) ) = θ τ (o i,y i ) D + τ Initial θ learned in meta training: min θ n i (o j,y j ) D train τ i ( L yj, f CAML (g(θ, D τ + i ))(o j ) ) 6

16 CAML - Algorithm. Algorithm 1 CAML training phase Require: α, β learning rate Hyper-parameters. k examples size (k-shot). 1: Randomly initialize θ 2: while not done do 3: Sample batch of tasks of size k. 4: for all τ i in batch do 5: Sample Di train and D + i s.t. Di train D + i = 6: Calculate task parameters with gradient decent: 7: θ i = θ α θ (o j,y j ) D L ( y + j, f CAML (θ)(o j ) ) i 8: end for 9: Update θ θ β θ τ i batch 10: end while (o j,y j ) D L ( y i train j, f CAML (θ i )(o j ) ) 7

17 CAML - Algorithm. Algorithm 2 CAML test phase Require: D + new positive examples of success for a new task. Require: θ Pre-trained meta-learner parameters. Require: α learning rate Hyper-parameters. 1: Adapt parameters with gradient decent: 2: θ = θ α θ (o j,y j ) D + new L( y j, f CAML (θ)(o j ) ) 3: return f CAML (θ ) 8

18 From observation classifier to rewards. f C (o) [0, 1] interpreted as probability of o to ba a successful execution of the task. Directly use the f C output as reward. To reduce the effect of false positives. Use a threshold t (0, 1) and set f C (o) 0 if f C (o) < t. 9

19 Experimental results - Single task relative position 10

20 Experimental results - Multi task relative position 11

21 Experimental evaluation competitors Pixel distance: Measure the l 2 distance between observation and successful observation. Latent space distance: Measure distance in a learned latent space using an auto encoder. Here Deep spatial autoencoders for visuomotor learning by Finn et al Oracle: Use the ground truth if available to get an upper bound of performance (only applied in the rope manipulation domain). 12

22 Experimental results - Relative position 13

23 Experimental results - Relative position planning costs 14

24 Experimental results - Rope manipulation 15

25 Experimental results - Rope manipulation 15

26 Experimental results - 3D navigation 16

27 Experimental results - 3D navigation 16

28 Conclusion 17

29 Conclusion Model that can achieve rapid adaptation. 17

30 Conclusion Model that can achieve rapid adaptation. Internal representation that is broadly suitable to many tasks. 17

31 Conclusion Model that can achieve rapid adaptation. Internal representation that is broadly suitable to many tasks. If tasks have distinct visual concept unlikely that meta-learning will acquire useful knowledge. 17

32 Conclusion Model that can achieve rapid adaptation. Internal representation that is broadly suitable to many tasks. If tasks have distinct visual concept unlikely that meta-learning will acquire useful knowledge. Experiments showed good performance on vision-based manipulation skills. 17

33 Thanks! 17

34 Bibliography Finn, C., Abbeel, P., and Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. arxiv preprint arxiv: Xie, A., Singh, A., Levine, S., and Finn, C. (2018). Few-shot goal inference for visuomotor learning and planning. CoRR, abs/

Few-shot learning with KRR

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

More information

Convolutional Neural Networks

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»

More information

Reptile: a Scalable Metalearning Algorithm

Reptile: a Scalable Metalearning Algorithm Reptile: a Scalable Metalearning Algorithm Alex Nichol and John Schulman OpenAI {alex, joschu}@openai.com Abstract This paper considers metalearning problems, where there is a distribution of tasks, and

More information

Bayesian Deep Learning

Bayesian Deep Learning Bayesian Deep Learning Mohammad Emtiyaz Khan AIP (RIKEN), Tokyo http://emtiyaz.github.io emtiyaz.khan@riken.jp June 06, 2018 Mohammad Emtiyaz Khan 2018 1 What will you learn? Why is Bayesian inference

More information

CONCEPT LEARNING WITH ENERGY-BASED MODELS

CONCEPT LEARNING WITH ENERGY-BASED MODELS CONCEPT LEARNING WITH ENERGY-BASED MODELS Igor Mordatch OpenAI San Francisco mordatch@openai.com 1 OVERVIEW Many hallmarks of human intelligence, such as generalizing from limited experience, abstract

More information

Domain adaptation for deep learning

Domain adaptation for deep learning What you saw is not what you get Domain adaptation for deep learning Kate Saenko Successes of Deep Learning in AI A Learning Advance in Artificial Intelligence Rivals Human Abilities Deep Learning for

More information

Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks

Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks Towards a Data-driven Approach to Exploring Galaxy Evolution via Generative Adversarial Networks Tian Li tian.li@pku.edu.cn EECS, Peking University Abstract Since laboratory experiments for exploring astrophysical

More information

Deep Learning Lab Course 2017 (Deep Learning Practical)

Deep Learning Lab Course 2017 (Deep Learning Practical) Deep Learning Lab Course 207 (Deep Learning Practical) Labs: (Computer Vision) Thomas Brox, (Robotics) Wolfram Burgard, (Machine Learning) Frank Hutter, (Neurorobotics) Joschka Boedecker University of

More information

STA 414/2104: Lecture 8

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

More information

CS230: Lecture 9 Deep Reinforcement Learning

CS230: Lecture 9 Deep Reinforcement Learning CS230: Lecture 9 Deep Reinforcement Learning Kian Katanforoosh Menti code: 21 90 15 Today s outline I. Motivation II. Recycling is good: an introduction to RL III. Deep Q-Learning IV. Application of Deep

More information

arxiv: v1 [cs.lg] 24 Jul 2018

arxiv: v1 [cs.lg] 24 Jul 2018 Learning Plannable Representations with Causal InfoGAN Thanard Kurutach UC Berkeley Aviv Tamar UC Berkeley Ge Yang University of Chicago arxiv:1807.09341v1 [cs.lg] 24 Jul 2018 Stuart Russell UC Berkeley

More information

Learning Dexterity Matthias Plappert SEPTEMBER 6, 2018

Learning Dexterity Matthias Plappert SEPTEMBER 6, 2018 Learning Dexterity Matthias Plappert SEPTEMBER 6, 2018 OpenAI OpenAI is a non-profit AI research company, discovering and enacting the path to safe artificial general intelligence. OpenAI OpenAI is a non-profit

More information

OPTIMIZATION METHODS IN DEEP LEARNING

OPTIMIZATION METHODS IN DEEP LEARNING Tutorial outline OPTIMIZATION METHODS IN DEEP LEARNING Based on Deep Learning, chapter 8 by Ian Goodfellow, Yoshua Bengio and Aaron Courville Presented By Nadav Bhonker Optimization vs Learning Surrogate

More information

Classification goals: Make 1 guess about the label (Top-1 error) Make 5 guesses about the label (Top-5 error) No Bounding Box

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

More information

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 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

More information

Least Mean Squares Regression

Least Mean Squares Regression Least Mean Squares Regression Machine Learning Spring 2018 The slides are mainly from Vivek Srikumar 1 Lecture Overview Linear classifiers What functions do linear classifiers express? Least Squares Method

More information

Discovering Unknown Unknowns of Predictive Models

Discovering Unknown Unknowns of Predictive Models Discovering Unknown Unknowns of Predictive Models Himabindu Lakkaraju Stanford University himalv@cs.stanford.edu Rich Caruana rcaruana@microsoft.com Ece Kamar eckamar@microsoft.com Eric Horvitz horvitz@microsoft.com

More information

TUTORIAL PART 1 Unsupervised Learning

TUTORIAL PART 1 Unsupervised Learning TUTORIAL PART 1 Unsupervised Learning Marc'Aurelio Ranzato Department of Computer Science Univ. of Toronto ranzato@cs.toronto.edu Co-organizers: Honglak Lee, Yoshua Bengio, Geoff Hinton, Yann LeCun, Andrew

More information

Introduction to Machine Learning

Introduction to Machine Learning Introduction to Machine Learning CS4731 Dr. Mihail Fall 2017 Slide content based on books by Bishop and Barber. https://www.microsoft.com/en-us/research/people/cmbishop/ http://web4.cs.ucl.ac.uk/staff/d.barber/pmwiki/pmwiki.php?n=brml.homepage

More information

PAC Learning Introduction to Machine Learning. Matt Gormley Lecture 14 March 5, 2018

PAC Learning Introduction to Machine Learning. Matt Gormley Lecture 14 March 5, 2018 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University PAC Learning Matt Gormley Lecture 14 March 5, 2018 1 ML Big Picture Learning Paradigms:

More information

Policy Gradient Methods. February 13, 2017

Policy Gradient Methods. February 13, 2017 Policy Gradient Methods February 13, 2017 Policy Optimization Problems maximize E π [expression] π Fixed-horizon episodic: T 1 Average-cost: lim T 1 T r t T 1 r t Infinite-horizon discounted: γt r t Variable-length

More information

Machine Learning Basics

Machine Learning Basics Security and Fairness of Deep Learning Machine Learning Basics Anupam Datta CMU Spring 2019 Image Classification Image Classification Image classification pipeline Input: A training set of N images, each

More information

CS Machine Learning Qualifying Exam

CS Machine Learning Qualifying Exam CS Machine Learning Qualifying Exam Georgia Institute of Technology March 30, 2017 The exam is divided into four areas: Core, Statistical Methods and Models, Learning Theory, and Decision Processes. There

More information

Boosting & Deep Learning

Boosting & Deep Learning Boosting & Deep Learning Ensemble Learning n So far learning methods that learn a single hypothesis, chosen form a hypothesis space that is used to make predictions n Ensemble learning à select a collection

More information

Predictive analysis on Multivariate, Time Series datasets using Shapelets

Predictive analysis on Multivariate, Time Series datasets using Shapelets 1 Predictive analysis on Multivariate, Time Series datasets using Shapelets Hemal Thakkar Department of Computer Science, Stanford University hemal@stanford.edu hemal.tt@gmail.com Abstract Multivariate,

More information

Machine Learning. Boris

Machine Learning. Boris Machine Learning Boris Nadion boris@astrails.com @borisnadion @borisnadion boris@astrails.com astrails http://astrails.com awesome web and mobile apps since 2005 terms AI (artificial intelligence)

More information

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 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

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others) Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)

More information

Probabilistic Graphical Models

Probabilistic Graphical Models 10-708 Probabilistic Graphical Models Homework 3 (v1.1.0) Due Apr 14, 7:00 PM Rules: 1. Homework is due on the due date at 7:00 PM. The homework should be submitted via Gradescope. Solution to each problem

More information

Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions

Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions 2018 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 18) Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions Authors: S. Scardapane, S. Van Vaerenbergh,

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

Bayesian Networks (Part I)

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,

More information

An overview of deep learning methods for genomics

An overview of deep learning methods for genomics An overview of deep learning methods for genomics Matthew Ploenzke STAT115/215/BIO/BIST282 Harvard University April 19, 218 1 Snapshot 1. Brief introduction to convolutional neural networks What is deep

More information

Probabilistic Mixture of Model-Agnostic Meta-Learners

Probabilistic Mixture of Model-Agnostic Meta-Learners Probabilistic Mixture of Model-Agnostic Meta-Learners Prasanna Sattigeri psattig@us.ibm.com Soumya Ghosh ghoshso@us.ibm.com Abhishe Kumar abhishe@inductivebias.net Karthieyan Natesan Ramamurthy natesa@us.ibm.com

More information

UNSUPERVISED LEARNING

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

More information

Least Mean Squares Regression. Machine Learning Fall 2018

Least Mean Squares Regression. Machine Learning Fall 2018 Least Mean Squares Regression Machine Learning Fall 2018 1 Where are we? Least Squares Method for regression Examples The LMS objective Gradient descent Incremental/stochastic gradient descent Exercises

More information

CS229 Supplemental Lecture notes

CS229 Supplemental Lecture notes CS229 Supplemental Lecture notes John Duchi 1 Boosting We have seen so far how to solve classification (and other) problems when we have a data representation already chosen. We now talk about a procedure,

More information

Convolutional Neural Networks. Srikumar Ramalingam

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/

More information

Learning Deep Architectures for AI. Part II - Vijay Chakilam

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

More information

Variational Autoencoders (VAEs)

Variational Autoencoders (VAEs) September 26 & October 3, 2017 Section 1 Preliminaries Kullback-Leibler divergence KL divergence (continuous case) p(x) andq(x) are two density distributions. Then the KL-divergence is defined as Z KL(p

More information

Bayesian Semi-supervised Learning with Deep Generative Models

Bayesian Semi-supervised Learning with Deep Generative Models Bayesian Semi-supervised Learning with Deep Generative Models Jonathan Gordon Department of Engineering Cambridge University jg801@cam.ac.uk José Miguel Hernández-Lobato Department of Engineering Cambridge

More information

Deep Reinforcement Learning: Policy Gradients and Q-Learning

Deep Reinforcement Learning: Policy Gradients and Q-Learning Deep Reinforcement Learning: Policy Gradients and Q-Learning John Schulman Bay Area Deep Learning School September 24, 2016 Introduction and Overview Aim of This Talk What is deep RL, and should I use

More information

Lecture 14: Deep Generative Learning

Lecture 14: Deep Generative Learning Generative Modeling CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 14: Deep Generative Learning Density estimation Reconstructing probability density function using samples Bohyung Han

More information

INF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018

INF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018 Machine learning for image classification Lecture 14: Reinforcement learning May 9, 2018 Page 3 Outline Motivation Introduction to reinforcement learning (RL) Value function based methods (Q-learning)

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

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

More information

Tennis player segmentation for semantic behavior analysis

Tennis player segmentation for semantic behavior analysis Proposta di Tennis player segmentation for semantic behavior analysis Architettura Software per Robot Mobili Vito Renò, Nicola Mosca, Massimiliano Nitti, Tiziana D Orazio, Donato Campagnoli, Andrea Prati,

More information

MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October,

MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October, MIDTERM: CS 6375 INSTRUCTOR: VIBHAV GOGATE October, 23 2013 The exam is closed book. You are allowed a one-page cheat sheet. Answer the questions in the spaces provided on the question sheets. If you run

More information

Value Function Methods. CS : Deep Reinforcement Learning Sergey Levine

Value Function Methods. CS : Deep Reinforcement Learning Sergey Levine Value Function Methods CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 2 is due in one week 2. Remember to start forming final project groups and writing your proposal! Proposal

More information

On the power and the limits of evolvability. Vitaly Feldman Almaden Research Center

On the power and the limits of evolvability. Vitaly Feldman Almaden Research Center On the power and the limits of evolvability Vitaly Feldman Almaden Research Center Learning from examples vs evolvability Learnable from examples Evolvable Parity functions The core model: PAC [Valiant

More information

Deep Learning for Computer Vision

Deep Learning for Computer Vision Deep Learning for Computer Vision Lecture 4: Curse of Dimensionality, High Dimensional Feature Spaces, Linear Classifiers, Linear Regression, Python, and Jupyter Notebooks Peter Belhumeur Computer Science

More information

The Perceptron Algorithm 1

The Perceptron Algorithm 1 CS 64: Machine Learning Spring 5 College of Computer and Information Science Northeastern University Lecture 5 March, 6 Instructor: Bilal Ahmed Scribe: Bilal Ahmed & Virgil Pavlu Introduction The Perceptron

More information

Trust Region Policy Optimization

Trust Region Policy Optimization Trust Region Policy Optimization Yixin Lin Duke University yixin.lin@duke.edu March 28, 2017 Yixin Lin (Duke) TRPO March 28, 2017 1 / 21 Overview 1 Preliminaries Markov Decision Processes Policy iteration

More information

PILCO: A Model-Based and Data-Efficient Approach to Policy Search

PILCO: A Model-Based and Data-Efficient Approach to Policy Search PILCO: A Model-Based and Data-Efficient Approach to Policy Search (M.P. Deisenroth and C.E. Rasmussen) CSC2541 November 4, 2016 PILCO Graphical Model PILCO Probabilistic Inference for Learning COntrol

More information

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści

Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?

More information

Experiments on the Consciousness Prior

Experiments on the Consciousness Prior Yoshua Bengio and William Fedus UNIVERSITÉ DE MONTRÉAL, MILA Abstract Experiments are proposed to explore a novel prior for representation learning, which can be combined with other priors in order to

More information

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks Emily Denton 1, Soumith Chintala 2, Arthur Szlam 2, Rob Fergus 2 1 New York University 2 Facebook AI Research Denotes equal

More information

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 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

More information

Empirical Risk Minimization Algorithms

Empirical Risk Minimization Algorithms Empirical Risk Minimization Algorithms Tirgul 2 Part I November 2016 Reminder Domain set, X : the set of objects that we wish to label. Label set, Y : the set of possible labels. A prediction rule, h:

More information

How to do backpropagation in a brain

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

More information

Latent Variable Models

Latent Variable Models Latent Variable Models Stefano Ermon, Aditya Grover Stanford University Lecture 5 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 5 1 / 31 Recap of last lecture 1 Autoregressive models:

More information

Forward and Reverse Gradient-Based Hyperparameter Optimization

Forward and Reverse Gradient-Based Hyperparameter Optimization Forward and Reverse Gradient-Based Hyperparameter Optimization Luca Franceschi 1,2, Michele Donini 1, Paolo Frasconi 3, Massimiliano Pontil 1,2 1 Istituto Italiano di Tecnologia, Genoa, Italy 2 Dept of

More information

Variational Autoencoders. Presented by Alex Beatson Materials from Yann LeCun, Jaan Altosaar, Shakir Mohamed

Variational Autoencoders. Presented by Alex Beatson Materials from Yann LeCun, Jaan Altosaar, Shakir Mohamed Variational Autoencoders Presented by Alex Beatson Materials from Yann LeCun, Jaan Altosaar, Shakir Mohamed Contents 1. Why unsupervised learning, and why generative models? (Selected slides from Yann

More information

Non-Linearity. CS 188: Artificial Intelligence. Non-Linear Separators. Non-Linear Separators. Deep Learning I

Non-Linearity. CS 188: Artificial Intelligence. Non-Linear Separators. Non-Linear Separators. Deep Learning I Non-Linearity CS 188: Artificial Intelligence Deep Learning I Instructors: Pieter Abbeel & Anca Dragan --- University of California, Berkeley [These slides were created by Dan Klein, Pieter Abbeel, Anca

More information

Based on the original slides of Hung-yi Lee

Based on the original slides of Hung-yi Lee Based on the original slides of Hung-yi Lee Google Trends Deep learning obtains many exciting results. Can contribute to new Smart Services in the Context of the Internet of Things (IoT). IoT Services

More information

Generalized Zero-Shot Learning with Deep Calibration Network

Generalized Zero-Shot Learning with Deep Calibration Network Generalized Zero-Shot Learning with Deep Calibration Network Shichen Liu, Mingsheng Long, Jianmin Wang, and Michael I.Jordan School of Software, Tsinghua University, China KLiss, MOE; BNRist; Research

More information

Boosting: Algorithms and Applications

Boosting: Algorithms and Applications Boosting: Algorithms and Applications Lecture 11, ENGN 4522/6520, Statistical Pattern Recognition and Its Applications in Computer Vision ANU 2 nd Semester, 2008 Chunhua Shen, NICTA/RSISE Boosting Definition

More information

BACKPROPAGATION. Neural network training optimization problem. Deriving backpropagation

BACKPROPAGATION. Neural network training optimization problem. Deriving backpropagation BACKPROPAGATION Neural network training optimization problem min J(w) w The application of gradient descent to this problem is called backpropagation. Backpropagation is gradient descent applied to J(w)

More information

Learning theory. Ensemble methods. Boosting. Boosting: history

Learning theory. Ensemble methods. Boosting. Boosting: history Learning theory Probability distribution P over X {0, 1}; let (X, Y ) P. We get S := {(x i, y i )} n i=1, an iid sample from P. Ensemble methods Goal: Fix ɛ, δ (0, 1). With probability at least 1 δ (over

More information

STA 414/2104: Lecture 8

STA 414/2104: Lecture 8 STA 414/2104: Lecture 8 6-7 March 2017: Continuous Latent Variable Models, Neural networks Delivered by Mark Ebden With thanks to Russ Salakhutdinov, Jimmy Ba and others Outline Continuous latent variable

More information

Statistical Learning Theory. Part I 5. Deep Learning

Statistical Learning Theory. Part I 5. Deep Learning Statistical Learning Theory Part I 5. Deep Learning Sumio Watanabe Tokyo Institute of Technology Review : Supervised Learning Training Data X 1, X 2,, X n q(x,y) =q(x)q(y x) Information Source Y 1, Y 2,,

More information

Logistic Regression. Robot Image Credit: Viktoriya Sukhanova 123RF.com

Logistic Regression. Robot Image Credit: Viktoriya Sukhanova 123RF.com Logistic Regression These slides were assembled by Eric Eaton, with grateful acknowledgement of the many others who made their course materials freely available online. Feel free to reuse or adapt these

More information

Lecture 4: Perceptrons and Multilayer Perceptrons

Lecture 4: Perceptrons and Multilayer Perceptrons Lecture 4: Perceptrons and Multilayer Perceptrons Cognitive Systems II - Machine Learning SS 2005 Part I: Basic Approaches of Concept Learning Perceptrons, Artificial Neuronal Networks Lecture 4: Perceptrons

More information

Midterm, Fall 2003

Midterm, Fall 2003 5-78 Midterm, Fall 2003 YOUR ANDREW USERID IN CAPITAL LETTERS: YOUR NAME: There are 9 questions. The ninth may be more time-consuming and is worth only three points, so do not attempt 9 unless you are

More information

Unsupervised Learning

Unsupervised Learning CS 3750 Advanced Machine Learning hkc6@pitt.edu Unsupervised Learning Data: Just data, no labels Goal: Learn some underlying hidden structure of the data P(, ) P( ) Principle Component Analysis (Dimensionality

More information

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials Philipp Krähenbühl and Vladlen Koltun Stanford University Presenter: Yuan-Ting Hu 1 Conditional Random Field (CRF) E x I = φ u

More information

Prediction of Citations for Academic Papers

Prediction of Citations for Academic Papers 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050

More information

Machine Teaching. for Personalized Education, Security, Interactive Machine Learning. Jerry Zhu

Machine Teaching. for Personalized Education, Security, Interactive Machine Learning. Jerry Zhu Machine Teaching for Personalized Education, Security, Interactive Machine Learning Jerry Zhu NIPS 2015 Workshop on Machine Learning from and for Adaptive User Technologies Supervised Learning Review D:

More information

9 Classification. 9.1 Linear Classifiers

9 Classification. 9.1 Linear Classifiers 9 Classification This topic returns to prediction. Unlike linear regression where we were predicting a numeric value, in this case we are predicting a class: winner or loser, yes or no, rich or poor, positive

More information

Auto-Encoding Variational Bayes

Auto-Encoding Variational Bayes Auto-Encoding Variational Bayes Diederik P Kingma, Max Welling June 18, 2018 Diederik P Kingma, Max Welling Auto-Encoding Variational Bayes June 18, 2018 1 / 39 Outline 1 Introduction 2 Variational Lower

More information

Reinforcement Learning for NLP

Reinforcement Learning for NLP Reinforcement Learning for NLP Advanced Machine Learning for NLP Jordan Boyd-Graber REINFORCEMENT OVERVIEW, POLICY GRADIENT Adapted from slides by David Silver, Pieter Abbeel, and John Schulman Advanced

More information

ECE521 Lectures 9 Fully Connected 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

More information

Machine Learning. Neural Networks. (slides from Domingos, Pardo, others)

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

More information

Neural networks and optimization

Neural networks and optimization Neural networks and optimization Nicolas Le Roux Criteo 18/05/15 Nicolas Le Roux (Criteo) Neural networks and optimization 18/05/15 1 / 85 1 Introduction 2 Deep networks 3 Optimization 4 Convolutional

More information

Generative models for missing value completion

Generative models for missing value completion Generative models for missing value completion Kousuke Ariga Department of Computer Science and Engineering University of Washington Seattle, WA 98105 koar8470@cs.washington.edu Abstract Deep generative

More information

Chapter 20. Deep Generative Models

Chapter 20. Deep Generative Models Peng et al.: Deep Learning and Practice 1 Chapter 20 Deep Generative Models Peng et al.: Deep Learning and Practice 2 Generative Models Models that are able to Provide an estimate of the probability distribution

More information

Deep Generative Models for Graph Generation. Jian Tang HEC Montreal CIFAR AI Chair, Mila

Deep Generative Models for Graph Generation. Jian Tang HEC Montreal CIFAR AI Chair, Mila Deep Generative Models for Graph Generation Jian Tang HEC Montreal CIFAR AI Chair, Mila Email: jian.tang@hec.ca Deep Generative Models Goal: model data distribution p(x) explicitly or implicitly, where

More information

From Binary to Multiclass Classification. CS 6961: Structured Prediction Spring 2018

From Binary to Multiclass Classification. CS 6961: Structured Prediction Spring 2018 From Binary to Multiclass Classification CS 6961: Structured Prediction Spring 2018 1 So far: Binary Classification We have seen linear models Learning algorithms Perceptron SVM Logistic Regression Prediction

More information

Variational Inference for Monte Carlo Objectives

Variational Inference for Monte Carlo Objectives Variational Inference for Monte Carlo Objectives Andriy Mnih, Danilo Rezende June 21, 2016 1 / 18 Introduction Variational training of directed generative models has been widely adopted. Results depend

More information

Loss Functions and Optimization. Lecture 3-1

Loss Functions and Optimization. Lecture 3-1 Lecture 3: Loss Functions and Optimization Lecture 3-1 Administrative Assignment 1 is released: http://cs231n.github.io/assignments2017/assignment1/ Due Thursday April 20, 11:59pm on Canvas (Extending

More information

HOMEWORK #4: LOGISTIC REGRESSION

HOMEWORK #4: LOGISTIC REGRESSION HOMEWORK #4: LOGISTIC REGRESSION Probabilistic Learning: Theory and Algorithms CS 274A, Winter 2018 Due: Friday, February 23rd, 2018, 11:55 PM Submit code and report via EEE Dropbox You should submit a

More information

Segmentation of Cell Membrane and Nucleus using Branches with Different Roles in Deep Neural Network

Segmentation of Cell Membrane and Nucleus using Branches with Different Roles in Deep Neural Network Segmentation of Cell Membrane and Nucleus using Branches with Different Roles in Deep Neural Network Tomokazu Murata 1, Kazuhiro Hotta 1, Ayako Imanishi 2, Michiyuki Matsuda 2 and Kenta Terai 2 1 Meijo

More information

Deep Learning & Neural Networks Lecture 4

Deep Learning & Neural Networks Lecture 4 Deep Learning & Neural Networks Lecture 4 Kevin Duh Graduate School of Information Science Nara Institute of Science and Technology Jan 23, 2014 2/20 3/20 Advanced Topics in Optimization Today we ll briefly

More information

Imitation Learning by Coaching. Abstract

Imitation Learning by Coaching. Abstract Imitation Learning by Coaching He He Hal Daumé III Department of Computer Science University of Maryland College Park, MD 20740 {hhe,hal}@cs.umd.edu Abstract Jason Eisner Department of Computer Science

More information

Robotics 2. AdaBoost for People and Place Detection. Kai Arras, Cyrill Stachniss, Maren Bennewitz, Wolfram Burgard

Robotics 2. AdaBoost for People and Place Detection. Kai Arras, Cyrill Stachniss, Maren Bennewitz, Wolfram Burgard Robotics 2 AdaBoost for People and Place Detection Kai Arras, Cyrill Stachniss, Maren Bennewitz, Wolfram Burgard v.1.1, Kai Arras, Jan 12, including material by Luciano Spinello and Oscar Martinez Mozos

More information

Supervised Learning. George Konidaris

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,

More information

Reward-modulated inference

Reward-modulated inference Buck Shlegeris Matthew Alger COMP3740, 2014 Outline Supervised, unsupervised, and reinforcement learning Neural nets RMI Results with RMI Types of machine learning supervised unsupervised reinforcement

More information

Memory-Augmented Attention Model for Scene Text Recognition

Memory-Augmented Attention Model for Scene Text Recognition Memory-Augmented Attention Model for Scene Text Recognition Cong Wang 1,2, Fei Yin 1,2, Cheng-Lin Liu 1,2,3 1 National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences

More information

FAST ADAPTATION IN GENERATIVE MODELS WITH GENERATIVE MATCHING NETWORKS

FAST ADAPTATION IN GENERATIVE MODELS WITH GENERATIVE MATCHING NETWORKS FAST ADAPTATION IN GENERATIVE MODELS WITH GENERATIVE MATCHING NETWORKS Sergey Bartunov & Dmitry P. Vetrov National Research University Higher School of Economics (HSE), Yandex Moscow, Russia ABSTRACT We

More information

Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning

Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning Sangdoo Yun 1 Jongwon Choi 1 Youngjoon Yoo 2 Kimin Yun 3 and Jin Young Choi 1 1 ASRI, Dept. of Electrical and Computer Eng.,

More information

Collaborative topic models: motivations cont

Collaborative topic models: motivations cont Collaborative topic models: motivations cont Two topics: machine learning social network analysis Two people: " boy Two articles: article A! girl article B Preferences: The boy likes A and B --- no problem.

More information