Prune and Distill: Similar reformatting of image information along rat visual cortex and deep neural networks
28. listopadu 2022
Řečníci
Paolo Muratore
Řečník · 0 sledujících
Sina Tafazoli
Řečník · 0 sledujících
Eugenio Piasini
Řečník · 0 sledujících
Alessandro Laio
Řečník · 0 sledujících
Davide Zoccolan
Řečník · 0 sledujících
O prezentaci
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…
Organizátor
NeurIPS 2022
Účet · 952 sledujících
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Pre-trained Models for Learned DBMS Components
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Panel
Zhlédnout později
Salomey Osei, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
SymbolicGPT: A Generative Transformer Model for Symbolic Regression
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Orient: Submodular Mutual Information Measures for Data Subset Selection under Distribution Shift
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
A counterfactual simulation model of causal judgments about social agents
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Parti 1: The Lifelong Learnign Problem: Overview of currently used settings and benchmarks
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 3 diváků, což je 0.3 %