Prune and Distill: Similar reformatting of image information along rat visual cortex and deep neural networks
Nov 28, 2022
Speakers
Paolo Muratore
Speaker · 0 followers
Sina Tafazoli
Speaker · 0 followers
Eugenio Piasini
Speaker · 0 followers
Alessandro Laio
Speaker · 0 followers
Davide Zoccolan
Speaker · 0 followers
About
Visual object recognition has been extensively studied in both neuroscience and computer vision. Recently, the most popular class of artificial systems for this task, deep convolutional neural networks (CNNs), has been shown to provide excellent models for its functional analogue in the brain, the ventral stream in visual cortex. This has prompted questions on what, if any, are the common principles underlying the reformatting of visual information as it flows through a CNN or the ventral stream. Here we consider some prominent statistical patterns that are known to exist in the internal representations of either CNNs or the visual cortex and look for them in the other system. We show that intrinsic dimensionality (ID) of object representations along the rat homologue of the ventral stream presents two distinct expansion-contraction phases, as previously shown for CNNs. Conversely, in CNNs, we show that training results in both distillation and active pruning (mirroring the increase in ID) of low- to middle-level image information in single units, as representations gain the ability to support invariant discrimination, in agreement with previous observations in rat visual cortex. Taken together, our findings suggest that CNNs and visual cortex share a similarly tight relationship between dimensionality expansion/reduction of object representations and reformatting of image information.Visual object recognition has been extensively studied in both neuroscience and computer vision. Recently, the most popular class of artificial systems for this task, deep convolutional neural networks (CNNs), has been shown to provide excellent models for its functional analogue in the brain, the ventral stream in visual cortex. This has prompted questions on what, if any, are the common principles underlying the reformatting of visual information as it flows through a CNN or the ventral stream…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
SNN-RAT: Robustness-enhanced Spiking Neural Network through Regularized Adversarial Training
Watch later
Jianhao Ding, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
a-ReQ: Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Generative multitask learning mitigates target-causing confounding
Watch later
Taro Makino, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Sponsor Networking Session
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
Watch later
Songkai Xue, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
TransTab: Learning Transferable Tabular Transformers Across Tables
Watch later
Zifeng Wang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%