English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Generalization in data-driven models of primary visual cortex

Lurz, K.-K., Bashiri, M., Willeke, K., Jagadish, A., Wang, E., Walker, E., et al. (2021). Generalization in data-driven models of primary visual cortex. In Ninth International Conference on Learning Representations (ICLR 2021).

Item is

Basic

show hide
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-
OA-Status:
Not specified

Creators

show
hide
 Creators:
Lurz, K-K, Author
Bashiri, M, Author
Willeke, K, Author
Jagadish, A1, Author                 
Wang, E, Author
Walker, EY, Author
Cadena, SA, Author
Muhammad, T, Author
Cobos, E, Author
Tolias, AS, Author           
Ecker, AS, Author           
Sinz, FH, Author           
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Deep neural networks (DNN) have set new standards at predicting responses of neural populations to visual input. Most such DNNs consist of a convolutional network (core) shared across all neurons which learns a representation of neural computation in visual cortex and a neuron-specific readout that linearly combines the relevant features in this representation. The goal of this paper is to test whether such a representation is indeed generally characteristic for visual cortex, i.e. generalizes between animals of a species, and what factors contribute to obtaining such a generalizing core. To push all non-linear computations into the core where the generalizing cortical features should be learned, we devise a novel readout that reduces the number of parameters per neuron in the readout by up to two orders of magnitude compared to the previous state-of-the-art. It does so by taking advantage of retinotopy and learns a Gaussian distribution over the neuron’s receptive field position. With this new readout we train our network on neural responses from mouse primary visual cortex (V1) and obtain a gain in performance of 7% compared to the previous state-of-the-art network. We then investigate whether the convolutional core indeed captures general cortical features by using the core in transfer learning to a different animal. When transferring a core trained on thousands of neurons from various animals and scans we exceed the performance of training directly on that animal by 12%, and outperform a commonly used VGG16 core pre-trained on imagenet by 33%. In addition, transfer learning with our data-driven core is more data-efficient than direct training, achieving the same performance with only 40% of the data. Our model with its novel readout thus sets a new state-of-the-art for neural response prediction in mouse visual cortex from natural images, generalizes between animals, and captures better characteristic cortical features than current task-driven pre-training approaches such as VGG16.

Details

show
hide
Language(s):
 Dates: 2021-05
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Ninth International Conference on Learning Representations (ICLR 2021)
Place of Event: Wien, Austria
Start-/End Date: 2021-05-03 - 2021-05-07

Legal Case

show

Project information

show

Source 1

show
hide
Title: Ninth International Conference on Learning Representations (ICLR 2021)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -