Article

Direct-fit to nature: an evolutionary perspective on biological (and artificial) neural networks

2019-09-10

Abstract excerpt

Evolution is a blind fitting process by which organisms, over generations, adapt to the niches of an ever-changing environment. Does the mammalian brain use similar brute-force fitting processes to learn how to perceive and act upon the world? Recent advances in training deep neural networks has exposed the power of optimizing millions of synaptic weights to map millions of observations along ecologically relevant...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ae90e225-cc48-5cd7-93a2-c6ee34fc22a6
DOI: 10.1101/764258

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Direct-fit to nature: an evolutionary perspective on biological (and artificial) neural networksDOI 10.1101/764258Read

AI-discovered tuning laws explain neuronal population code geometrySemantic proximity Read

Abstract representations emerge naturally in neural networks trained to perform multiple tasksSemantic proximity Read

AI-Discovered Cognitive Models Reveal Novel Insights into Human and Animal LearningSemantic proximity Read

Predicting Brain Morphogenesis via Physics-Transfer LearningSemantic proximity Read

Shared Representations of Stability in Humans, Supervised & Unsupervised Deep Neural NetworksSemantic proximity Read

Model metamers illuminate divergences between biological and artificial neural networksSemantic proximity Read

Bayesian natural selection and the evolution of perceptual systems.Semantic proximity Read

A controller-peripheral architecture and costly energy principle for learningSemantic proximity Read

A single dynamical property can account for the capacity to learn, from artificial networks to the mammalian brainSemantic proximity Read

Large-scale hyperparameter search for predicting human brain responses in the Algonauts challengeSemantic proximity Read

Beyond Deep Learning—Space, Time, and EmergenceSemantic proximity Read

Leveraging synthetic data produced from museum specimens to train adaptable species classification modelsSemantic proximity Read