The Multiple Subnetwork Hypothesis: Enabling Multidomain Learning by Isolating Task-Specific Subnetworks in Feedforward Neural Networks

07/18/2022
by   Jacob Renn, et al.
7

Neural networks have seen an explosion of usage and research in the past decade, particularly within the domains of computer vision and natural language processing. However, only recently have advancements in neural networks yielded performance improvements beyond narrow applications and translated to expanded multitask models capable of generalizing across multiple data types and modalities. Simultaneously, it has been shown that neural networks are overparameterized to a high degree, and pruning techniques have proved capable of significantly reducing the number of active weights within the network while largely preserving performance. In this work, we identify a methodology and network representational structure which allows a pruned network to employ previously unused weights to learn subsequent tasks. We employ these methodologies on well-known benchmarking datasets for testing purposes and show that networks trained using our approaches are able to learn multiple tasks, which may be related or unrelated, in parallel or in sequence without sacrificing performance on any task or exhibiting catastrophic forgetting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/29/2023

When Deep Learning Meets Polyhedral Theory: A Survey

In the past decade, deep learning became the prevalent methodology for p...
research
06/22/2020

Continual Learning in Recurrent Neural Networks with Hypernetworks

The last decade has seen a surge of interest in continual learning (CL),...
research
03/07/2020

Synaptic Metaplasticity in Binarized Neural Networks

While deep neural networks have surpassed human performance in multiple ...
research
04/08/2020

CALM: Continuous Adaptive Learning for Language Modeling

Training large language representation models has become a standard in t...
research
03/06/2021

TextMage: The Automated Bangla CaptionGenerator Based On Deep Learning

Neural Networks and Deep Learning have seen an upsurge of research in th...
research
05/29/2023

Deep Predictive Coding with Bi-directional Propagation for Classification and Reconstruction

This paper presents a new learning algorithm, termed Deep Bi-directional...
research
10/15/2020

TextMage: The Automated Bangla Caption Generator Based On Deep Learning

Neural Networks and Deep Learning have seen an upsurge of research in th...

Please sign up or login with your details

Forgot password? Click here to reset