technique

Disentangled RNNs

techniqueactiveprovisionaldisentangled-rnns-eee73873·1 events·first seen 6d ago

Aliases: Disentangled RNNs

Co-occurring entities

ATLAS: Active Theory Learning for Automated Science Atlas

More like this (12)

Disentangled Representation Learning Dynamic Short Convolutions Improve Transformers Pretraining Recurrent Networks without Recurrence decoupled reinforcement learning Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models Recurrent Neural Network Alternating Token-Weighted Unlearning Graph Neural Network Encoder Sparse Autoencoders ResNet Recursive Language Models (RLMs)Relational Deep Learning

Recent events (1)

5arXiv · cs.LG·6d ago·source ↗

ATLAS: Active learning framework for automated discovery of interpretable behavioral models in cognitive science

ATLAS (Active Theory Learning for Automated Science) is a new active learning framework that iterates between generating mechanistic hypotheses as sparse neural network ensembles and designing maximally informative experiments to distinguish between them. The system is tested on recovering reinforcement learning agents from behavioral data in bandit tasks, achieving 5-10x sample efficiency improvements over random experimentation and matching expert-designed experiments from the literature. The work targets automated scientific discovery in cognitive science, with potential generalization to other domains requiring mechanistic modeling.

Evaluation and Benchmarking ATLAS: Active Theory Learning for Automated Science Disentangled RNNs Atlas