Ensemble perspective for understanding temporal credit assignment

02/07/2021
by   Wenxuan Zou, et al.
0

Recurrent neural networks are widely used for modeling spatio-temporal sequences in both nature language processing and neural population dynamics. However, understanding the temporal credit assignment is hard. Here, we propose that each individual connection in the recurrent computation is modeled by a spike and slab distribution, rather than a precise weight value. We then derive the mean-field algorithm to train the network at the ensemble level. The method is then applied to classify handwritten digits when pixels are read in sequence, and to the multisensory integration task that is a fundamental cognitive function of animals. Our model reveals important connections that determine the overall performance of the network. The model also shows how spatio-temporal information is processed through the hyperparameters of the distribution, and moreover reveals distinct types of emergent neural selectivity. It is thus promising to study the temporal credit assignment in recurrent neural networks from the ensemble perspective.

READ FULL TEXT

page 8

page 15

research
09/08/2023

Meta predictive learning model of natural languages

Large language models based on self-attention mechanisms have achieved a...
research
01/10/2020

Learning credit assignment

Deep learning has achieved impressive prediction accuracies in a variety...
research
12/26/2017

Chaos-guided Input Structuring for Improved Learning in Recurrent Neural Networks

Anatomical studies demonstrate that brain reformats input information to...
research
10/21/2021

Cortico-cerebellar networks as decoupling neural interfaces

The brain solves the credit assignment problem remarkably well. For cred...
research
02/05/2016

Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks

The current paper proposes a novel neural network model for recognizing ...
research
02/09/2021

Pairwise Weights for Temporal Credit Assignment

How much credit (or blame) should an action taken in a state get for a f...
research
12/02/2022

Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory

Credit assignment problem of neural networks refers to evaluating the cr...

Please sign up or login with your details

Forgot password? Click here to reset