interpretability and visualization of deep neural networks
play

Interpretability and Visualization of Deep Neural Networks Au Aude - PowerPoint PPT Presentation

Jan 15, 2023 •16 likes •356 views

Interpretability and Visualization of Deep Neural Networks Au Aude Oliva MI MIT Convoluti tional Neura ral Netw twork rks convolution max-pooling normalization full connected Alexnet Ea Each ch laye yer learns prog ogressive

  1. Interpretability and Visualization of Deep Neural Networks Au Aude Oliva MI MIT

  4. Convoluti tional Neura ral Netw twork rks convolution max-pooling normalization full connected Alexnet Ea Each ch laye yer learns prog ogressive vely y mor ore com complex x features Krizhevsky et al (2012).NIPS

  5. What t did th the netw twork rk learn rn ? pl places2.csail.mi mit.edu du

  6. Compari ring Object t and Scenes CNNs Zhou, Khosla, at al (2015). ICLR

  7. Data driven approach inspired by Neuroscience: Empirical receptive field

  8. Pipeline for r esti timati ting th the Recepti tive Fields: Goal is to identify which regions of the image lead to the high unit activations. Di Discr crepancy cy map per unit 5000 occluded versions Zhou, Khosla, at al (2015). ICLR

  9. Pipeline for r esti timati ting th the Recepti tive Fields To To consolidate the information from several images, we ce center the discr crepancy cy map arou ound the spatial loca ocation on of of the uni unit t tha hat c caus used ed t the m he maximum um a activation f n for t the g he given i en image. e. Th Then we average the re-ce centered discr crepancy cy maps to o ge generate t the f final r recept ptive f field o d of e each gi given u unit. . Zhou, Khosla, at al (2015). ICLR

  10. Annota tati ting th the Semanti tics of Units ts Pool5, unit 76; Label: ocean; Type: scene; Prec ecision: n: 93% 93%

  11. Annota tati ting th the Semanti tics of Units ts Pool5, unit 13; Label: Lamps; Type: object; Pr Precisi sion: 84%

  12. Annota tati ting th the Semanti tics of Units ts Pool5, unit 77; Label: legs; Type: object part; Prec ecision: n: 96% 96%

  13. La Layer 1

  14. La Layer 2

  15. La Layer 4

  16. La Layer 5

  29. Visualizing Units & Connections http://people.csail.mit.edu/torralba/research/drawCNN/drawNet.html

  30. http://netdissect.csail.mit.edu/

  31. Corr Corresp spon ondence ce betw tween deep mod odels an and human man brai ain ?

  32. Algorithmic-specific fMRI searchlight analysis A A spati atial ally unbias ased view of th the relati ations in similari arity ty stru tructu ture betwe be ween m mode dels a and f d fMRI I Voxels within Vo searchlight se fMRI fMRI vs. vs voxe vo xel voxe voxel Spea Sp earman n Correla Co latio ion Layer 3 La vs vs. Cichy, Khosla, Pantazis, Torralba & Oliva, A. (2016). Scientific Reports.

  33. Spatiotemporal maps of co correlations be between huma man br brain and d mode model layers Pari rieta tal Ventra tral Layers 1-2 Layers 2-4 Layers 5-8 Cichy, Khosla, Pantazis, Torralba & Oliva, A. (2016). Scientific Reports.

  34. Co Compari ring Natu tura ral and Arti rtifici cial De Deep Neural al Netwo works • New f New fiel elds of ds of exper expertise: se: Cognitive / Clinical / Social / Perceptual Comput Computat ational onal Exper Experiment mental alist st • St Stud udyi ying ng t the i he imp mplement ementat ation on that works best for performing specific tasks • Char Charact acter erizi zing t ng the net he networ ork behavi k behavior or when it is adapting, compromised or enhanced • Exp Explor oring ng t the al he alter ernat natives ves that have not been taken by biological systems Antonio An io Davi Da vid Ad Adit itya Ra Rados doslaw Bo Bolei Kh Khosla To Torralba Ba Bau Cic Cichy Zhou Zho

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

Full-Gradient Representation for Neural Network Visualization Suraj Srinivas Francois Fleuret

Full-Gradient Representation for Neural Network Visualization Suraj Srinivas Francois Fleuret

Full-Gradient Representation for Neural Network Visualization Suraj Srinivas Francois Fleuret Idiap Research Institute & EPFL Why Interpretability for Deep Learning? Why does the model think Deep this chest x-ray shows Pneumonia

556 views • 19 slides
Anatomy and Interpretability of Neural Networks Leon Yin ~ Data Scientist | Research Engineer

Anatomy and Interpretability of Neural Networks Leon Yin ~ Data Scientist | Research Engineer

Anatomy and Interpretability of Neural Networks Leon Yin ~ Data Scientist | Research Engineer SMaPP and CDS PRG 2017-11-15 Todays talking points: How do Neural Networks work? How can we see what theyre learning? Discussion about

403 views • 19 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
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
Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite

Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite

Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery NeurIPS 2020 Workshop Tackling Climate Change with Machine Learning Thomas Y. Chen Computer Vision, Satellite Imagery, and Building

401 views • 16 slides
Neural Networks for Machine Learning Lecture 15c Deep autoencoders for document retrieval and

Neural Networks for Machine Learning Lecture 15c Deep autoencoders for document retrieval and

Neural Networks for Machine Learning Lecture 15c Deep autoencoders for document retrieval and visualization Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed How to find documents that are similar to a

853 views • 11 slides
Deep Neural Networks and Molecular Dynamics Roberto Car Princeton University MAX Conference

Deep Neural Networks and Molecular Dynamics Roberto Car Princeton University MAX Conference

Deep Neural Networks and Molecular Dynamics Roberto Car Princeton University MAX Conference ICTP, Trieste, Jan 29-31 2018 Deep Neural Networks When properly trained, deep NN are capable of learning the complex functional dependence of

442 views • 17 slides
CS7015 (Deep Learning) : Lecture 13 Visualizing Convolutional Neural Networks, Guided

CS7015 (Deep Learning) : Lecture 13 Visualizing Convolutional Neural Networks, Guided

CS7015 (Deep Learning) : Lecture 13 Visualizing Convolutional Neural Networks, Guided Backpropagation, Deep Dream, Deep Art, Fooling Convolutional Neural Networks Mitesh M. Khapra Department of Computer Science and Engineering Indian Institute

1.07k views • 72 slides
Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Deep Neural Networks and Deep Reinforcement Learning Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and Courville [chapt. 6,7,8]; AIMA [sect. 21.1-21.3]; Sutton and Barto, Reinforcement Learning: an

527 views • 35 slides
Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Learning in Neural Networks w 1,3 w 3,5 1 3 5 w w 1,4 3,6 w w 2,3 4,5 2 4 6 w w 2,4 4,6 Class #18: Back-Propagation; } A neural network can learn a classification function by Tuning Hyper-Parameters adjusting its weights to

259 views • 4 slides
Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the

Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the

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

852 views • 63 slides
Bayesian hierarchical models Bruno Nicenboim / Shravan Vasishth 2020-03-14 1 Bayesian

Bayesian hierarchical models Bruno Nicenboim / Shravan Vasishth 2020-03-14 1 Bayesian

Bayesian hierarchical models Bruno Nicenboim / Shravan Vasishth 2020-03-14 1 Bayesian hierarchical models (also known as multilevel or mixed-effects models) 2 Bayesian hierarchical models (also known as multilevel or mixed-effects models)

890 views • 43 slides
Mthodes algbriques pour le contrle optimal en Imagerie Rsonance Magntique Bernard

Mthodes algbriques pour le contrle optimal en Imagerie Rsonance Magntique Bernard

Mthodes algbriques pour le contrle optimal en Imagerie Rsonance Magntique Bernard Bonnard 1,2 Jean-Charles Faugre 3 Alain Jacquemard 1 Jrmy Rouot 4 Mohab Safey El Din 3 Thibaut Verron 5 1. Universit de Bourgogne-Franche

1.07k views • 64 slides
Coordinate Transformations in Parietal Cortex Computational Models of Neural Systems Lecture 7.1

Coordinate Transformations in Parietal Cortex Computational Models of Neural Systems Lecture 7.1

Coordinate Transformations in Parietal Cortex Computational Models of Neural Systems Lecture 7.1 David S. Touretzky November, 2017 Outline Anderson: parietal cells represent locations of visual stimuli. Zipser and Anderson: a backprop

539 views • 42 slides
BLINATUMOMAB: Esperienza di Bologna Stefania Paolini, MD, PhD

BLINATUMOMAB: Esperienza di Bologna Stefania Paolini, MD, PhD

BLINATUMOMAB: Esperienza di Bologna Stefania Paolini, MD, PhD Department of Experimental, Diagnos7c, and Specialty Medicine Bologna University Medical School

342 views • 22 slides
April 5, 2017 Crystal Parks and Recreation 244 Acres of Parkland 27 Parks Potential

April 5, 2017 Crystal Parks and Recreation 244 Acres of Parkland 27 Parks Potential

April 5, 2017 Crystal Parks and Recreation 244 Acres of Parkland 27 Parks Potential Classification of Parks Passive Neighborhood (8) (13) Crystal Parks Community Destination (4) (2) Passive (8) Little to no development Have

528 views • 41 slides
Yun-Hee Park 1 , Arastoo Pour Biazar 1 , Richard T. McNider 1 , Bright Dornblaser 3 , Maudood Khan

Yun-Hee Park 1 , Arastoo Pour Biazar 1 , Richard T. McNider 1 , Bright Dornblaser 3 , Maudood Khan

Yun-Hee Park 1 , Arastoo Pour Biazar 1 , Richard T. McNider 1 , Bright Dornblaser 3 , Maudood Khan 2 , Kevin Doty 1 1. University of Alabama in Huntsville 2. University Space Research Association (USRA) 3. Texas Commission on Environmental

498 views • 29 slides
FAST: Quick Application Launch on Solid-State Drives Yongsoo Joo 1 , Junhee Ryu 2 , Sangsoo Park

FAST: Quick Application Launch on Solid-State Drives Yongsoo Joo 1 , Junhee Ryu 2 , Sangsoo Park

FAST: Quick Application Launch on Solid-State Drives Yongsoo Joo 1 , Junhee Ryu 2 , Sangsoo Park 1 , and Kang G. Shin 1,3 1 Ewha Womans University, Korea 2 Seoul National University, Korea 3 University of Michigan, USA Application Launch Delay

402 views • 36 slides
Hibachi: A Cooperative Hybrid Cache with NVRAM and DRAM for Storage Arrays Ziqi Fan, Fenggang Wu,

Hibachi: A Cooperative Hybrid Cache with NVRAM and DRAM for Storage Arrays Ziqi Fan, Fenggang Wu,

Hibachi: A Cooperative Hybrid Cache with NVRAM and DRAM for Storage Arrays Ziqi Fan, Fenggang Wu, Dongchul Park 1 , Jim Diehl, Doug Voigt 2 , and David H.C. Du University of Minnesota, 1 Intel, 2 HP Enterprise May 18, 2017 C enter for R esearch in

875 views • 20 slides

More recommend