Copertina

Separating the what and how of compositional computation to enable reuse and continual learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shan, Haozhe, Minni, Sun, Duncker, Lea
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Neurons and Cognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Transformer brain encoders explain human high-level visual responses
di: Adeli, Hossein, et al.
Pubblicazione: (2025)

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

Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems
di: Hu, Amber, et al.
Pubblicazione: (2024)

Brain-language fusion enables interactive neural readout and in-silico experimentation
di: Bosch, Victoria, et al.
Pubblicazione: (2025)

Neural timescales from a computational perspective
di: Zeraati, Roxana, et al.
Pubblicazione: (2024)

Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects
di: Bishop, William E., et al.
Pubblicazione: (2026)

Riemannian Geometry for the classification of brain states with intracortical brain-computer interfaces
di: Marin-Llobet, Arnau, et al.
Pubblicazione: (2025)

Scaling and context steer LLMs along the same computational path as the human brain
di: Raugel, Joséphine, et al.
Pubblicazione: (2025)

An introduction to reinforcement learning for neuroscience
di: Jensen, Kristopher T.
Pubblicazione: (2023)

When does compositional structure yield compositional generalization? A kernel theory
di: Lippl, Samuel, et al.
Pubblicazione: (2024)

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

Compositional meta-learning through probabilistic task inference
di: Bakermans, Jacob J. W., et al.
Pubblicazione: (2025)

Emergent Riemannian geometry over learning discrete computations on continuous manifolds
di: Brandon, Julian, et al.
Pubblicazione: (2025)

Reward function compression facilitates goal-dependent reinforcement learning
di: Molinaro, Gaia, et al.
Pubblicazione: (2025)

Multi-intention Inverse Q-learning for Interpretable Behavior Representation
di: Zhu, Hao, et al.
Pubblicazione: (2023)

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

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

Using machine learning methods to predict cognitive age from psychophysiological tests
di: Tyurina, Daria D., et al.
Pubblicazione: (2025)

Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
di: Nan, Mu, et al.
Pubblicazione: (2026)

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

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

Cortex and subcortex play distinct roles over learning when cortical memory is limited
di: Farrell, Matthew, et al.
Pubblicazione: (2026)

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

Mapping minds not averages: a scalable subject-specific manifold learning framework for neuroimaging data
di: Geenjaar, Eloy, et al.
Pubblicazione: (2025)

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

Deep multimodal saliency parcellation of cerebellar pathways: linking microstructure and individual function through explainable multitask learning
di: Tchetchenian, Ari, et al.
Pubblicazione: (2024)

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

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

EEG-estimated functional connectivity, and not behavior, differentiates Parkinson's patients from health controls during the Simon conflict task
di: Sun, Xiaoxiao, et al.
Pubblicazione: (2024)

EEG-Deformer: A Dense Convolutional Transformer for Brain-computer Interfaces
di: Ding, Yi, et al.
Pubblicazione: (2024)

Physiologically-Informed Predictability of a Teammate's Future Actions Forecasts Team Performance
di: Qin, Yinuo, et al.
Pubblicazione: (2025)

On efficient computation in active inference
di: Paul, Aswin, et al.
Pubblicazione: (2023)

Discretization of continuous input spaces in the hippocampal autoencoder
di: Amil, Adrian F., et al.
Pubblicazione: (2024)

A Data-Driven Method to Map the Functional Organisation of Human Brain White Matter
di: Sun, Yifei, et al.
Pubblicazione: (2026)

Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics
di: Mei, Jie, et al.
Pubblicazione: (2025)

Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation
di: Sun, Hongze, et al.
Pubblicazione: (2025)

Dissociating model architectures from inference computations
di: Sajid, Noor, et al.
Pubblicazione: (2025)

Separation of Neural Drives to Muscles from Transferred Polyfunctional Nerves using Implanted Micro-electrode Arrays
di: Ferrante, Laura, et al.
Pubblicazione: (2024)

NeuroXVocal: Detection and Explanation of Alzheimer's Disease through Non-invasive Analysis of Picture-prompted Speech
di: Ntampakis, Nikolaos, et al.
Pubblicazione: (2025)

Does Feedback Alignment Work at Biological Timescales?
di: Bacvanski, Marc Gong, et al.
Pubblicazione: (2025)