Neuroevolutionary Transfer Learning of Deep Recurrent Neural Networks through Network-Aware Adaptation

06/04/2020
by   AbdElRahman ElSaid, et al.
0

Transfer learning entails taking an artificial neural network (ANN) that is trained on a source dataset and adapting it to a new target dataset. While this has been shown to be quite powerful, its use has generally been restricted by architectural constraints. Previously, in order to reuse and adapt an ANN's internal weights and structure, the underlying topology of the ANN being transferred across tasks must remain mostly the same while a new output layer is attached, discarding the old output layer's weights. This work introduces network-aware adaptive structure transfer learning (N-ASTL), an advancement over prior efforts to remove this restriction. N-ASTL utilizes statistical information related to the source network's topology and weight distribution in order to inform how new input and output neurons are to be integrated into the existing structure. Results show improvements over prior state-of-the-art, including the ability to transfer in challenging real-world datasets not previously possible and improved generalization over RNNs trained without transfer.

READ FULL TEXT

page 5

page 7

page 8

research
09/16/2020

Improved Neural Network Monte Carlo Simulation

The algorithm for Monte Carlo simulation of parton-level events based on...
research
06/21/2023

Introspective Action Advising for Interpretable Transfer Learning

Transfer learning can be applied in deep reinforcement learning to accel...
research
07/15/2020

Visualizing Transfer Learning

We provide visualizations of individual neurons of a deep image recognit...
research
02/10/2015

A HMAX with LLC for visual recognition

Today's high performance deep artificial neural networks (ANNs) rely hea...
research
09/27/2021

Spiking neural networks trained via proxy

We propose a new learning algorithm to train spiking neural networks (SN...
research
10/02/2018

Target Aware Network Adaptation for Efficient Representation Learning

This paper presents an automatic network adaptation method that finds a ...
research
02/21/2019

Incremental Transfer Learning in Two-pass Information Bottleneck based Speaker Diarization System for Meetings

The two-pass information bottleneck (TPIB) based speaker diarization sys...

Please sign up or login with your details

Forgot password? Click here to reset