Search Results for author:
Found 5 papers, 3 papers with code
Meta predictive learning model of languages in neural circuits
Therefore, our model provides a starting point to investigate the connection among brain computation, next-token prediction and general intelligence.
Statistical mechanics of continual learning: variational principle and mean-field potential
A variational Bayesian learning setting is thus proposed, where the neural networks are trained in a field-space, rather than gradient-ill-defined discrete-weight space, and furthermore, weight uncertainty is naturally incorporated, and modulates synaptic resources among tasks.
Emergence of hierarchical modes from deep learning
Large-scale deep neural networks consume expensive training costs, but the training results in less-interpretable weight matrices constructing the networks.
Ensemble perspective for understanding temporal credit assignment
Recurrent neural networks are widely used for modeling spatio-temporal sequences in both nature language processing and neural population dynamics.
Learning credit assignment
Therefore, our model learns the credit assignment leading to the decision, and predicts an ensemble of sub-networks that can accomplish the same task, thereby providing insights toward understanding the macroscopic behavior of deep learning through the lens of distinct roles of synaptic weights.
