Long short-term relevance learning

06/21/2021
by   Bram van de Weg, et al.
0

To incorporate prior knowledge as well as measurement uncertainties in the traditional long short term memory (LSTM) neural networks, an efficient sparse Bayesian training algorithm is introduced to the network architecture. The proposed scheme automatically determines relevant neural connections and adapts accordingly, in contrast to the classical LSTM solution. Due to its flexibility, the new LSTM scheme is less prone to overfitting, and hence can approximate time dependent solutions by use of a smaller data set. On a structural nonlinear finite element application we show that the self-regulating framework does not require prior knowledge of a suitable network architecture and size, while ensuring satisfying accuracy at reasonable computational cost.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/03/2018

Auto-ML Deep Learning for Rashi Scripts OCR

In this work we propose an OCR scheme for manuscripts printed in Rashi f...
research
06/14/2023

Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loads

Deep Operator Network (DeepONet), a recently introduced deep learning op...
research
01/18/2019

DA-LSTM: A Long Short-Term Memory with Depth Adaptive to Non-uniform Information Flow in Sequential Data

Much sequential data exhibits highly non-uniform information distributio...
research
06/12/2018

Knowledge Amalgam: Generating Jokes and Quotes Together

Generating humor and quotes are very challenging problems in the field o...
research
02/03/2020

On-Device Information Extraction from SMS using Hybrid Hierarchical Classification

Cluttering of SMS inbox is one of the serious problems that users today ...
research
06/21/2021

Brain tumor grade classification Using LSTM Neural Networks with Domain Pre-Transforms

The performance of image classification methodsheavily relies on the hig...

Please sign up or login with your details

Forgot password? Click here to reset