arXiv AI August 3, 2026 By Martin N. P. Nilsson

Information Processing by Neuron Populations in the Central Nervous System: A Theory of the Mathematical Structure of Data and Operations

arXiv:2309. 02332v3 Announce Type: replace-cross Abstract: In the mammalian central nervous system, neurons are organized into populations communicating by spike trains propagating along axonal bundles.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 8

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders

arXiv:2606. 07007v1 Announce Type: cross Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs).

By Chenhao Zhang, Chris Lin, Su-In Lee

efficiency safety

arXiv AI

Jul 1

Creating Intelligence: A Computational Foundation for AGI

arXiv:2606. 31819v1 Announce Type: new Abstract: This work introduces a new computational theory of mind grounded in set theory and hyperdimensional computing.

By Peter Overmann

arXiv Machine Learning

2d ago

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

arXiv:2609.38998v1 Announce Type: new Abstract: A foundational principle of connectionism is that perception, action, and cognition emerge from parallel computations among simple, interconnected unit...

By Lukas Braun, Erin Grant, Andrew M. Saxe

safety

arXiv Machine Learning

Jul 13

How are linear representations learned? Exact solutions to the dynamics of abstraction

arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.

By William W. Yang, Andrew M. Saxe, Peter E. Latham

llms safety

arXiv Machine Learning

Jul 14

Emergent Generalization by Representation Learning in Artificial Neural Networks

arXiv:2607. 10430v1 Announce Type: cross Abstract: Dimensionality reduction has proven powerful for identifying neural manifolds, which are low-dimensional structures underlying high-dimensional neural activity.

By Hardik Rajpal, Dan Goodman

safety

arXiv Machine Learning

Jul 14

Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks

arXiv:2511. 02584v2 Announce Type: replace-cross Abstract: Associative memory, traditionally modeled by Hopfield networks, enables the retrieval of previously stored patterns from partial or noisy cues.

By Mark Bl\"umel, Andreas C. Schneider, Valentin Neuhaus, David A. Ehrlich, Marcel Graetz, Michael Wibral, Abdullah Makkeh, Viola Priesemann

benchmarks

One email a morning, machine-written

Related stories

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders

Creating Intelligence: A Computational Foundation for AGI

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

How are linear representations learned? Exact solutions to the dynamics of abstraction

Emergent Generalization by Representation Learning in Artificial Neural Networks

Redundancy Maximization as a Principle of Associative Memory Learning in Hopfield Networks