Trending

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Machine Learning

Neural and Evolutionary Computing

Neurons and Cognition

Biologically enforced disentangling in the brain

Disentangling with Biological Constraints: A Theory of Functional Cell Types

Neural representations are often highly sought after in both brains and machine learning.

We demonstrate these constraints lead to disentangling in a variety of tasks and architectures, including variational autoencoders.

We also use this theory to explain why the brain partitions its cells into distinct cell types such as grid and object-vector cells, and also explain when the brain instead entangles representations in response to entangled task factors.

Authors

James C.R. Whittington, Will Dorrell, Surya Ganguli, Timothy E.J. Behrens

Related Topics

Variational autoencoders

Disentangled representations

Neural representations

Read the Paper

Read Paper

Trending

Bookmarks

◐ Recommended Follows

Founder 42papers.com. Also bui...

Average CS student at ULL. I l...

More

◐ Latest Activity

More

Biologically enforced disentangling in the brain - 42Papers

Read Related Papers

Deep Autoencoders: From Understanding to Generalization Guarantees

Criticality of Deep Neural Networks with Infinity Approximation

Multiset-Equivalence in Deep Set Prediction

Self-supervised 3D shape variational autoencoder for latent representation of identity features

Intuitive Shape Editing in Latent Space

A Unified Approach to Variational Autoencoders and Stochastic Normalizing Flows via Markov Chains

Emergence of dynamic properties in network hyper-motifs

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks

Quantum Dynamics of a Recurrent Neural Network

Topological Regularization for Dense Prediction