Article overview: Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
Report
Ilya KuzovkinFollow
Sep. 11, 2015•0 likes•1,141 views
Article overview: Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
Sep. 11, 2015•0 likes•1,141 views
Download to read offline
Report
Science
The article presents the comparison of the complexity of the representation of visual features in the deep convolutional neural network and in our brain. DNN activity layer-by-layer is used to predict voxel activations and it is shown that lower layers of DNN are better at predicting V1,V2 and that higher layers of DNN are better in predicting activity in LO and higher areas of ventral stream. The result effectively demonstrates that layer-by-layer complexity of visual features we see in DNN is also present in the visual cortex.
Ilya KuzovkinFollow
Recommended
Kate Storrs - Closing the loop between biological and artificial vision - Cre...Luba Elliott
CVPR 2020 Workshop: Sparsity in the neocortex, and its implications for conti...Christy Maver
Sparsity In The Neocortex, And Its Implications For Machine LearningNumenta
Recurrent Neural Network WavefunctionsMohamedHibatAllah2
(Research Note) Delving deeper into convolutional neural networks for camera ...Jacky Liu
Scalable solutions for quantum communication networksBruno Fedrici, PhD
More Related Content
Viewers also liked
Article overview: Unsupervised Learning of Visual Structure Using Predictive ...Ilya Kuzovkin
Introduction to Computing on GPUIlya Kuzovkin
Learning RBM(Restricted Boltzmann Machine in Practice)Mad Scientists
Breaking the taboo: Legacy and in memory fundraisingNCVO - National Council for Voluntary Organisations
CHEN90023 Lachlan Russell 389374Lachlan Russell
A Journey to the Summit of KilimanjaroNanosecond
Similar to Article overview: Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
Ann first lectureCollege of Engineering poonjar
CVPR 2020 Workshop: Sparsity in the neocortex, and its implications for conti...Numenta
Consciousness, Graph theory and brain network tsc 2017Nir Lahav
Does the neocortex use grid cell-like mechanisms to learn the structure of ob...Numenta
01 Introduction to Neural Networks and Deep LearningAndres Mendez-Vazquez
Have We Missed Half of What the Neocortex Does? by Jeff Hawkins (12/15/2017)Numenta
Similar to Article overview: Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream(20)
![[PR12] Inception and Xception - Jaejun Yoo](https://cdn.slidesharecdn.com/ss_thumbnails/pr12inceptionandxception-jaejunyoo-170910140157-thumbnail.jpg?width=2048&height=1162&fit=bounds)
More from Ilya Kuzovkin
Understanding Information Processing in Human Brain by Interpreting Machine L...Ilya Kuzovkin
The Brain and the Modern AI: Drastic Differences and Curious SimilaritiesIlya Kuzovkin
The First Day at the Deep learning ZooIlya Kuzovkin
Intuitive Intro to Gödel's Incompleteness TheoremIlya Kuzovkin
Introduction to Machine Learning @ Mooncascade ML CampIlya Kuzovkin
Mastering the game of Go with deep neural networks and tree search (article o...Ilya Kuzovkin
Recently uploaded
ScooterLab - Griffin.pptxnathancone5537
NDDS UNIT 1 PART 3.pdfSUMIT TIWARI
g10science1stquartermodule1-200502160553 (2).pdfKhaoriVladir
The Effect of Third Party Implementations on ReproducibilityBalázs Hidasi
Animal Behaviour.pptxD. B. S. College Kanpur
subversiv › produktiv (QM).pdfpeterpur
Article overview: Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 1. Article overview by Ilya Kuzovkin Umut Güclü and Marcel A. J. van Gerven Computational Neuroscience Seminar University of Tartu 2015 Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 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 … pixels classes Linear “spider” “cat”
- 4. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream … pixels classes … hidden layer Non-linear “cat” “spider”
- 5. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream … pixels classes … hidden layer … hidden layer Deep “cat” “spider”
- 6. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream “spider” “cat” important feature
- 7. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream “spider” important feature RUN! “cat”
- 8. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream “spider” important feature RUN! Convolutional filter “cat”
- 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 … pixels classes … hidden layer … hidden layer … convolutional layer Deep Convolutional Neural Network “cat” “spider”
- 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. Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013 Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 16. Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013 Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 17. Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013 Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 18. Matthew D. Zeiler, Rob Fergus Visualizing and Understanding Convolutional Networks 2013 Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 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. 96x37x37=131,424
- 33. 96x37x37=131,424
- 34. 96x37x37=131,424256x17x17=73,984
- 35. 96x37x37=131,424256x17x17=73,984
- 36. 96x37x37=131,424256x17x17=73,984
- 37. 96x37x37=131,424256x17x17=73,984
- 38. 96x37x37=131,424256x17x17=73,984 Train linear regression model
- 39. 96x37x37=131,424256x17x17=73,984 Train linear regression model Test it
- 40. 96x37x37=131,424256x17x17=73,984 Train linear regression model Test it r = 0.22
- 41. 96x37x37=131,424256x17x17=73,984 Train linear regression model Test it r = 0.22 Train linear regression model Test it
- 42. 96x37x37=131,424256x17x17=73,984 Train linear regression model Test it r = 0.22 Train linear regression model Test it r = 0.67
- 43. 96x37x37=131,424256x17x17=73,984 Train linear regression model Test it r = 0.22 Train linear regression model Test it r = 0.67
- 44. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
- 45. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set
- 46. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . 1888
- 47. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . 1888
- 48. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888
- 49. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution .
- 50. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution . Low Mid High • blob • contrast • edge • contour • shape • texture • pattern • object • object part human-assigned to 9 categories
- 51. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution . Low Mid High • blob • contrast • edge • contour • shape • texture • pattern • object • object part human-assigned to 9 categories 1. Divide 1888 neurons into 9 categories
- 52. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution . Low Mid High • blob • contrast • edge • contour • shape • texture • pattern • object • object part human-assigned to 9 categories 1. Divide 1888 neurons into 9 categories ! 2. Predict activity of each voxel from group-by-group
- 53. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution . Low Mid High • blob • contrast • edge • contour • shape • texture • pattern • object • object part human-assigned to 9 categories 1. Divide 1888 neurons into 9 categories ! 2. Predict activity of each voxel from group-by-group ! 3. For each voxel find the group, which best predicts voxel’s activity
- 54. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution . Low Mid High • blob • contrast • edge • contour • shape • texture • pattern • object • object part human-assigned to 9 categories 1. Divide 1888 neurons into 9 categories ! 2. Predict activity of each voxel from group-by-group ! 3. For each voxel find the group, which best predicts voxel’s activity ! 4. Assign each of 1888 DNN neurons to a visual layer: V1, V2, V4, LO
- 55. NEXT COOL THING: CATEGORIES OF FEATURES … ImageNet validation set ... . . 1888 deconvolution . Low Mid High • blob • contrast • edge • contour • shape • texture • pattern • object • object part human-assigned to 9 categories 1. Divide 1888 neurons into 9 categories ! 2. Predict activity of each voxel from group-by-group ! 3. For each voxel find the group, which best predicts voxel’s activity ! 4. Assign each of 1888 DNN neurons to a visual layer: V1, V2, V4, LO ! 5. Map visual layers to categories
- 56. NEXT COOL THING: CATEGORIES OF FEATURES
- 57. OTHER RESULTS Correlation between predicted responses between pairs of voxel groups
- 58. OTHER RESULTS Selectivity of visual areas to feature maps of varying complexity
- 59. OTHER RESULTS Distribution of the receptive field centers
- 60. OTHER RESULTS Biclustering of voxels and feature maps
- 61. SUMMARY
- 62. An intracranial dataset we have. How to repeat the result?
- 63. An intracranial dataset we have. How to repeat the result? vs.