deep neural networks reveal a gradient in the complexity
play

Deep Neural Networks Reveal a Gradient in the Complexity of Neural - PowerPoint PPT Presentation

Jul 29, 2023 •216 likes •852 views

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Umut Gcl and Marcel A. J. van Gerven Article overview by Ilya Kuzovkin Computational Neuroscience Seminar University of Tartu

  1. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Umut Güclü and Marcel A. J. van Gerven Article overview by Ilya Kuzovkin Computational Neuroscience Seminar University of Tartu 2015

  2. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  3. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream classes “cat” “spider” … pixels Linear

  4. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream classes “cat” hidden layer … “spider” … pixels Non-linear

  5. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream classes “cat” hidden layer … hidden layer … “spider” … pixels Deep

  6. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream “cat” important feature “spider”

  7. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream “cat” important feature “spider” RUN!

  8. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream “cat” important feature “spider” Convolutional filter RUN!

  9. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Convolutional (and pooling) layer

  10. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream classes “cat” hidden layer … hidden layer … convolutional layer “spider” … … pixels Deep Convolutional Neural Network

  11. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  12. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  13. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  14. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013

  15. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013

  16. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013

  17. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013

  18. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013

  19. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  20. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream Two-stream hypothesis

  21. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  22. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  23. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  24. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  25. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  26. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  27. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream ?

  28. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  29. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  32. 96 x 37x 37 = 131,424

  33. 96 x 37x 37 = 131,424

  34. 96 x 37x 37 = 131,424 256 x 17x 17 = 73,984

  35. 96 x 37x 37 = 131,424 256 x 17x 17 = 73,984

  36. 96 x 37x 37 = 131,424 256 x 17x 17 = 73,984

  37. 96 x 37x 37 = 131,424 256 x 17x 17 = 73,984

  38. Train linear regression model 96 x 37x 37 = 131,424 256 x 17x 17 = 73,984

  39. Train linear regression model Test it 96 x 37x 37 = 131,424 256 x 17x 17 = 73,984

  40. 96 x 37x 37 = 131,424 Train linear regression model r = 0.22 Test it 256 x 17x 17 = 73,984

  41. 96 x 37x 37 = 131,424 Train linear regression model r = 0.22 Test it 256 x 17x 17 = 73,984 Train linear regression model Test it

  42. 96 x 37x 37 = 131,424 Train linear regression model r = 0.22 Test it 256 x 17x 17 = 73,984 Train linear regression model r = 0.67 Test it

  43. 96 x 37x 37 = 131,424 Train linear regression model r = 0.22 Test it 256 x 17x 17 = 73,984 Train linear regression model r = 0.67 Test it

  44. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream

  45. N EXT COOL THING : CATEGORIES OF FEATURES ImageNet validation set …

  46. N EXT COOL THING : CATEGORIES OF FEATURES ImageNet validation set ... . … 1888

  47. N EXT COOL THING : CATEGORIES OF FEATURES ImageNet validation set ... . … 1888

  48. N EXT COOL THING : CATEGORIES OF FEATURES ImageNet validation set ... . … 1888 .

  49. N EXT COOL THING : CATEGORIES OF FEATURES ImageNet validation set ... . … 1888 . . deconvolution

  50. N EXT COOL THING : CATEGORIES OF FEATURES ImageNet validation set ... . … 1888 . . deconvolution human-assigned to 9 categories Low Mid High • blob • contour • pattern • contrast • shape • object • edge • texture • object part

  51. N EXT COOL THING : CATEGORIES OF FEATURES 1. Divide 1888 neurons into 9 ImageNet validation set ... . categories … 1888 . . deconvolution human-assigned to 9 categories Low Mid High • blob • contour • pattern • contrast • shape • object • edge • texture • object part

  52. N EXT COOL THING : CATEGORIES OF FEATURES 1. Divide 1888 neurons into 9 ImageNet validation set ... . categories … 2. Predict activity of each voxel 1888 from group-by-group . . deconvolution human-assigned to 9 categories Low Mid High • blob • contour • pattern • contrast • shape • object • edge • texture • object part

  53. N EXT COOL THING : CATEGORIES OF FEATURES 1. Divide 1888 neurons into 9 ImageNet validation set ... . categories … 2. Predict activity of each voxel 1888 from group-by-group . 3. For each voxel find the group, which best predicts . voxel’s activity deconvolution human-assigned to 9 categories Low Mid High • blob • contour • pattern • contrast • shape • object • edge • texture • object part

  54. N EXT COOL THING : CATEGORIES OF FEATURES 1. Divide 1888 neurons into 9 ImageNet validation set ... . categories … 2. Predict activity of each voxel 1888 from group-by-group . 3. For each voxel find the group, which best predicts . voxel’s activity deconvolution human-assigned 4. Assign each of 1888 DNN to 9 categories neurons to a visual layer: V1, V2, V4, LO Low Mid High • blob • contour • pattern • contrast • shape • object • edge • texture • object part

  55. N EXT COOL THING : CATEGORIES OF FEATURES 1. Divide 1888 neurons into 9 ImageNet validation set ... . categories … 2. Predict activity of each voxel 1888 from group-by-group . 3. For each voxel find the group, which best predicts . voxel’s activity deconvolution human-assigned 4. Assign each of 1888 DNN to 9 categories neurons to a visual layer: V1, V2, V4, LO Low Mid High • blob • contour • pattern 5. Map visual layers to • contrast • shape • object categories • edge • texture • object part

  56. N EXT COOL THING : CATEGORIES OF FEATURES

  57. O THER RESULTS Correlation between predicted responses between pairs of voxel groups

  58. O THER RESULTS Selectivity of visual areas to feature maps of varying complexity

  59. O THER RESULTS Distribution of the receptive field centers

  60. O THER RESULTS Biclustering of voxels and feature maps

  61. S UMMARY

  62. An intracranial dataset we have. How to repeat the result?

  63. An intracranial dataset we have. How to repeat the result? vs.

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Deep Neural Networks CMSC 422 M ARINE C ARPUAT marine@cs.umd.edu Deep learning slides credit:

Deep Neural Networks CMSC 422 M ARINE C ARPUAT marine@cs.umd.edu Deep learning slides credit:

Deep Neural Networks CMSC 422 M ARINE C ARPUAT marine@cs.umd.edu Deep learning slides credit: Vlad Morariu Training (Deep) Neural Networks Computational graphs Improvements to gradient descent Stochastic gradient descent Momentum

814 views • 21 slides
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks Yuan Cao

Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks Yuan Cao

Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks Yuan Cao and Quanquan Gu Computer Science Department 1 / 14 Learning Over-parameterized DNNs Empirical observation on extremely wide deep neural networks

631 views • 14 slides
CS7015 (Deep Learning) : Lecture 3 Sigmoid Neurons, Gradient Descent, Feedforward Neural Networks,

CS7015 (Deep Learning) : Lecture 3 Sigmoid Neurons, Gradient Descent, Feedforward Neural Networks,

CS7015 (Deep Learning) : Lecture 3 Sigmoid Neurons, Gradient Descent, Feedforward Neural Networks, Representation Power of Feedforward Neural Networks Mitesh M. Khapra Department of Computer Science and Engineering Indian Institute of

869 views • 70 slides
Gradient Descent Finds Global Minima of Deep Neural Networks Simon S. Du, Jason D. Lee, Haochuan

Gradient Descent Finds Global Minima of Deep Neural Networks Simon S. Du, Jason D. Lee, Haochuan

Gradient Descent Finds Global Minima of Deep Neural Networks Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai 1 Empirical Observations on Empirical Risk Zhang et al, 2017, Understanding Deep Learning Requires Rethinking

264 views • 8 slides
Deep Learning: Training Juhan Nam Training Deep Neural Networks Forward (hidden unit

Deep Learning: Training Juhan Nam Training Deep Neural Networks Forward (hidden unit

GCT634/AI613: Musical Applications of Machine Learning (Fall 2020) Deep Learning: Training Juhan Nam Training Deep Neural Networks Forward (hidden unit activation) Parametric Gradient-based Learning Backward Non-parametric (gradient

650 views • 21 slides
Unraveling the mysteries of stochastic gradient descent on deep neural networks Pratik Chaudhari

Unraveling the mysteries of stochastic gradient descent on deep neural networks Pratik Chaudhari

Unraveling the mysteries of stochastic gradient descent on deep neural networks Pratik Chaudhari UCLA VISION LAB 1 The question measures disagreement of predictions with ground truth x = argmin f ( x ) Cat Dog ... x weights aka

496 views • 25 slides
CS480/680 Lecture 15: June 26, 2019 Deep Neural Networks [GBC] Chap. 6, 7, 8 University of

CS480/680 Lecture 15: June 26, 2019 Deep Neural Networks [GBC] Chap. 6, 7, 8 University of

CS480/680 Lecture 15: June 26, 2019 Deep Neural Networks [GBC] Chap. 6, 7, 8 University of Waterloo CS480/680 Spring 2019 Pascal Poupart 1 Outline Deep Neural Networks Gradient Vanishing Rectified linear units Overfitting

941 views • 25 slides
Deep Learning Primer Nishith Khandwala Neural Networks Overview Neural Network Basics

Deep Learning Primer Nishith Khandwala Neural Networks Overview Neural Network Basics

Deep Learning Primer Nishith Khandwala Neural Networks Overview Neural Network Basics Activation Functions Stochastic Gradient Descent (SGD) Regularization (Dropout) Training Tips and Tricks Neural Network (NN)

828 views • 45 slides
Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan

Deep Learning with Neural Networks The Structure and Optimization of Deep Neural Networks Allan Zelener Machine Learning Reading Group January 7 th 2016 The Graduate Center, CUNY Objectives Explain some of the trends of deep learning and

680 views • 44 slides
Fitting Neural Networks Gradient Descent and Stochastic Gradient Descent CS109A Introduction to

Fitting Neural Networks Gradient Descent and Stochastic Gradient Descent CS109A Introduction to

Fitting Neural Networks Gradient Descent and Stochastic Gradient Descent CS109A Introduction to Data Science Pavlos Protopapas, Kevin Rader and Chris Tanner New requirement for the final project: For the first time ever, researchers who submit

619 views • 34 slides
Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In

987 views • 40 slides
Visualizing and Interpreting Deep Neural Networks Bolei Zhou Department of Information

Visualizing and Interpreting Deep Neural Networks Bolei Zhou Department of Information

Visualizing and Interpreting Deep Neural Networks Bolei Zhou Department of Information Engineering The Chinese University of Hong Kong Deep Neural Networks are Everywhere Playing Go Making Medical Decision Understanding Scenes Deep Neural

1.1k views • 46 slides
On the Expressive Power of Deep Neural Networks Maithra Raghu, Ben Poole, Jon Kleinberg, Surya

On the Expressive Power of Deep Neural Networks Maithra Raghu, Ben Poole, Jon Kleinberg, Surya

On the Expressive Power of Deep Neural Networks Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, Jascha Sohl Dickstein Tom Brady Deep Neural Networks Recent successes in using Deep neural networks for image classification,

1.32k views • 17 slides
Outline Evolution of neurocomputing Artificial neural networks Feed forward

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides
Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova November 21, 2016 Neural Networks 2/20 Neural Networks 3/20 Neural Networks Neural computing requires a number of neurons , to be connected

813 views • 21 slides
Optimizing Deep Neural Networks Leena Chennuru Vankadara 26-10-2015 Table of Contents Neural

Optimizing Deep Neural Networks Leena Chennuru Vankadara 26-10-2015 Table of Contents Neural

Optimizing Deep Neural Networks Leena Chennuru Vankadara 26-10-2015 Table of Contents Neural Networks and loss surfaces Problems of Deep Architectures Optimization in Neural Networks Under fitting Proliferation of Saddle

1.67k views • 41 slides
The structure of the escaping set of a transcendental entire function Gwyneth Stallard (joint

The structure of the escaping set of a transcendental entire function Gwyneth Stallard (joint

The structure of the escaping set of a transcendental entire function Gwyneth Stallard (joint work with Phil Rippon) The Open University Postgraduate Conference in Complex Dynamics March 2015 The escaping set Definition The escaping set is I

650 views • 43 slides
Cantor bouquets in spiders webs Yannis Dourekas October 2, 2017 Universitat de Barcelona

Cantor bouquets in spiders webs Yannis Dourekas October 2, 2017 Universitat de Barcelona

Cantor bouquets in spiders webs Yannis Dourekas October 2, 2017 Universitat de Barcelona Basic defjnitions neighbourhood where the family of iterates is equicontinuous. infjnity under iteration. to infjnity as fast as possible: The

487 views • 11 slides
Important separators and parameterized algorithms Dniel Marx Humboldt-Universitt zu Berlin,

Important separators and parameterized algorithms Dniel Marx Humboldt-Universitt zu Berlin,

Important separators and parameterized algorithms Dniel Marx Humboldt-Universitt zu Berlin, Germany Methods for Discrete Structures February 7, 2011 Important separators and parameterized algorithms p.1/27 Overview Main message: Small

993 views • 77 slides
and preparing for flood emergency response Shirish Ravan United Nations Office for Outer Space

and preparing for flood emergency response Shirish Ravan United Nations Office for Outer Space

Bridging Science with Governance through the UN-SPIDER for flood risk management and preparing for flood emergency response Shirish Ravan United Nations Office for Outer Space Affairs United Nations Offices at Vienna www.unoosa.org United

888 views • 31 slides
THE SECURE PROJECT: SOME RESULTS COMING FROM THE RESEARCH OF SCIENCE CURRICULA AND TEACHERS

THE SECURE PROJECT: SOME RESULTS COMING FROM THE RESEARCH OF SCIENCE CURRICULA AND TEACHERS

THE SECURE PROJECT: SOME RESULTS COMING FROM THE RESEARCH OF SCIENCE CURRICULA AND TEACHERS AND LEARNERS OPINIONS ON SCIENCE EDUCATION . Job de Meyere (1) , Dagmara Sokolowska (2) , Elvira Folmer (3) , Barbara Rovsek (4) , Wim Peeters (5)

671 views • 44 slides
Q UANTUM G ROUP Introduction Quantum circuits Spiders ZX-calculus MBQC Survey Picturing

Q UANTUM G ROUP Introduction Quantum circuits Spiders ZX-calculus MBQC Survey Picturing

Introduction Quantum circuits Spiders ZX-calculus MBQC Survey Diagrammatic Reasoning and Quantum Computation Aleks Kissinger ACA, Kalamata November 4, 2015 Q UANTUM G ROUP Introduction Quantum circuits Spiders ZX-calculus MBQC

1.19k views • 101 slides
Assembly Programming Details CSE378 W INTER , 2001 55 Writing Assembly Programs The SPIM

Assembly Programming Details CSE378 W INTER , 2001 55 Writing Assembly Programs The SPIM

Assembly Programming Details CSE378 W INTER , 2001 55 Writing Assembly Programs The SPIM Assembler You generally shouldnt need to do this, but we spend time Mostly, the SPIM assembler is pretty faithful to the definition of learning

75 views • 3 slides
Instruction Set Architectures Part I: From C to MIPS Readings: 2.1- 2.14 1 Goals for this

Instruction Set Architectures Part I: From C to MIPS Readings: 2.1- 2.14 1 Goals for this

Instruction Set Architectures Part I: From C to MIPS Readings: 2.1- 2.14 1 Goals for this Class Understand how CPUs run programs How do we express the computation the CPU? How does the CPU execute it? How does the CPU

863 views • 75 slides

More recommend