Fixing the problems of deep neural networks will require better training data and learning algorithms

Drew Linsley, Thomas Serre
9/26/2023
cs.CVcs.AIcs.LG

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

Bowers and colleagues argue that DNNs are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as DNNs are becoming larger-scale and increasingly more accurate, and prescribe methods for building DNNs that can reliably model biological vision.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

87% match1 repo32026

Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?

85% match2023

Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment

85% match2024

Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations

84% match2026

Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks

82% match1 repo32024

Universal dimensions of visual representation

82% match1 repo102024

Cite this paper

@article{linsley2023fixing,
  title  = {Fixing the problems of deep neural networks will require better training data and learning algorithms},
  author = {Drew Linsley and Thomas Serre},
  year   = {2023},
  eprint = {2311.12819},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.12819v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.12819.svg)](https://codeofpaper.com/paper/2311.12819)

Discussion