Evaluating Biological Plausibility of Learning Algorithms the Lazy Way

Abstract

To which extent can successful machine learning inform our understanding of biological learning? One popular avenue of inquiry in recent years has been to directly map such algorithms into a realistic circuit implementation. Here we focus on learning in recurrent networks and investigate a range of learning algorithms. Our approach decomposes them into their computational building blocks and discusses their abstract potential as biological operations. This alternative strategy provides a “lazy” but principled way of evaluating ML ideas in terms of their biological plausibility

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Marschall et al. "Evaluating Biological Plausibility of Learning Algorithms the Lazy Way." NeurIPS 2019 Workshops: Neuro_AI, 2019.

Markdown

[Marschall et al. "Evaluating Biological Plausibility of Learning Algorithms the Lazy Way." NeurIPS 2019 Workshops: Neuro_AI, 2019.](https://mlanthology.org/neuripsw/2019/marschall2019neuripsw-evaluating/)

BibTeX

@inproceedings{marschall2019neuripsw-evaluating,
  title     = {{Evaluating Biological Plausibility of Learning Algorithms the Lazy Way}},
  author    = {Marschall, Owen and Cho, Kyunghyun and Savin, Cristina},
  booktitle = {NeurIPS 2019 Workshops: Neuro_AI},
  year      = {2019},
  url       = {https://mlanthology.org/neuripsw/2019/marschall2019neuripsw-evaluating/}
}