Cover Image

Category learning in deep neural networks: Information content and geometry of internal representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bonnasse-Gahot, Laurent, Nadal, Jean-Pierre
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Information Theory Neurons and Cognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence
by: Bonnasse-Gahot, Laurent, et al.
Published: (2026)

fMRI predictors based on language models of increasing complexity recover brain left lateralization
by: Bonnasse-Gahot, Laurent, et al.
Published: (2024)

The geometry of efficient codes: how rate-distortion trade-offs distort the latent representations of generative models
by: D'Amato, Leo, et al.
Published: (2024)

States as goal-directed concepts: an epistemic approach to state-representation learning
by: Amir, Nadav, et al.
Published: (2023)

Learning dynamic representations of the functional connectome in neurobiological networks
by: Dyballa, Luciano, et al.
Published: (2024)

Order parameters and phase transitions of continual learning in deep neural networks
by: Shan, Haozhe, et al.
Published: (2024)

Interpretable statistical representations of neural population dynamics and geometry
by: Gosztolai, Adam, et al.
Published: (2023)

Contribution of task-irrelevant stimuli to drift of neural representations
by: Pashakhanloo, Farhad
Published: (2025)

Large language models reorganize representational geometry during in-context learning
by: Xiong, Hua-Dong, et al.
Published: (2026)

Inferring stochastic low-rank recurrent neural networks from neural data
by: Pals, Matthijs, et al.
Published: (2024)

Prediction horizon shapes representations in predictive learning
by: Ratzon, Aviv, et al.
Published: (2025)

Graph neural networks uncover structure and functions underlying the activity of simulated neural assemblies
by: Allier, Cédric, et al.
Published: (2026)

Spectral-Stimulus Information for Self-Supervised Stimulus Encoding
by: Deighton, Jared, et al.
Published: (2024)

NLP4Neuro: Sequence-to-sequence learning for neural population decoding
by: Morra, Jacob J., et al.
Published: (2025)

Compositional Symmetry as Compression: Lie Pseudogroup Structure in Algorithmic Agents
by: Ruffini, Giulio
Published: (2025)

Information Capacity of EEG: Theoretical and Computational Limits of Recoverable Neural Information
by: Rao, Ishir
Published: (2025)

Quantifying information stored in synaptic connections rather than in firing activities of neural networks
by: Fan, Xinhao, et al.
Published: (2024)

HDGL: A hierarchical dynamic graph representation learning model for brain disorder classification
by: Jalali, Parnian, et al.
Published: (2023)

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry
by: Bozkurt, Bariscan, et al.
Published: (2023)

Active learning of neural population dynamics using two-photon holographic optogenetics
by: Wagenmaker, Andrew, et al.
Published: (2024)

Unsupervised learning of multiscale switching dynamical system models from multimodal neural data
by: Kim, DongKyu, et al.
Published: (2025)

Association-sensory spatiotemporal hierarchy and functional gradient-regularised recurrent neural network with implications for schizophrenia
by: Abulikemu, Subati, et al.
Published: (2025)

Oja's plasticity rule overcomes several challenges of training neural networks under biological constraints
by: Shervani-Tabar, Navid, et al.
Published: (2024)

Use-dependent Biases as Optimal Action under Information Bottleneck
by: Deng, Hokin, et al.
Published: (2024)

Emergent time-keeping mechanisms in a deep reinforcement learning agent performing an interval timing task
by: Pednekar, Amrapali, et al.
Published: (2025)

A ghost mechanism: An analytical model of abrupt learning in recurrent networks
by: Dinc, Fatih, et al.
Published: (2025)

An Information-Theoretic Framework For Optimizing Experimental Design To Distinguish Probabilistic Neural Codes
by: Kuo, Po-Chen, et al.
Published: (2026)

Machine learning approaches to uncover the neural mechanisms of motivated behaviour: from ADHD to individual differences in effort and reward sensitivity
by: Trinh, Nam
Published: (2026)

A rank decomposition for the topological classification of neural representations
by: Beshkov, Kosio, et al.
Published: (2024)

Rate-Distortion Signatures of Generalization and Information Trade-offs
by: Caglar, Leyla Roksan, et al.
Published: (2026)

A Quantifiable Information-Processing Hierarchy Provides a Necessary Condition for Detecting Agency
by: Kagan, Brett J., et al.
Published: (2026)

ML-PWS: Estimating the Mutual Information Between Experimental Time Series Using Neural Networks
by: Reinhardt, Manuel, et al.
Published: (2025)

Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
by: Huang, Ann, et al.
Published: (2024)

On periodic distributed representations using Fourier embeddings
by: Chouinard, Jakeb
Published: (2026)

Unsupervised discovery of the shared and private geometry in multi-view data
by: Koukuntla, Sai, et al.
Published: (2024)

Deep learning and whole-brain networks for biomarker discovery: modeling the dynamics of brain fluctuations in resting-state and cognitive tasks
by: Roffet, Facundo, et al.
Published: (2024)

The dynamic interplay between in-context and in-weight learning in humans and neural networks
by: Russin, Jacob, et al.
Published: (2024)

Stimulus symmetries can confound representational similarity analyses
by: Pashakhanloo, Farhad, et al.
Published: (2026)

Representation biases: will we achieve complete understanding by analyzing representations?
by: Lampinen, Andrew Kyle, et al.
Published: (2025)

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning
by: Chavlis, Spyridon, et al.
Published: (2024)