paper-with-me

홈 › Papers

An Empirical Exploration of Deep Recurrent Connections and Memory Cells Using Neuro-Evolution

2019-09-20 · Travis J. Desell, AbdElRahman A. ElSaid, Alexander G. Ororbia

Neuro-evolution and neural architecture search algorithms have gained increasing interest due to the challenges involved in designing optimal artificial neural networks (ANNs). While these algorithms have been shown to possess the potential to outperform the best human crafted architectures, a less common use of them is as a tool for analysis of ANN structural components and connectivity structures. In this work, we focus on this particular use-case to develop a rigorous examination and comparison framework for analyzing recurrent neural networks (RNNs) applied to time series prediction using the novel neuro-evolutionary process known as Evolutionary eXploration of Augmenting Memory Models (EXAMM). Specifically, we use our EXAMM-based analysis to investigate the capabilities of recurrent memory cells and the generalization ability afforded by various complex recurrent connectivity patterns that span one or more steps in time, i.e., deep recurrent connections. EXAMM, in this study, was used to train over 10.56 million RNNs in 5,280 repeated experiments with varying components. While many modern, often hand-crafted RNNs rely on complex memory cells (which have internal recurrent connections that only span a single time step) operating under the assumption that these sufficiently latch information and handle long term dependencies, our results show that networks evolved with deep recurrent connections perform significantly better than those without. More importantly, in some cases, the best performing RNNs consisted of only simple neurons and deep time skip connections, without any memory cells. These results strongly suggest that utilizing deep time skip connections in RNNs for time series data prediction not only deserves further, dedicated study, but also demonstrate the potential of neuro-evolution as a means to better study, understand, and train effective RNNs.

📄 PDF Abstract BibTeX arXiv:1909.09502

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture SearchTime SeriesTime Series AnalysisTime Series Prediction

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

A bio-inspired bistable recurrent cell allows for long-lasting memory

2020-06-09 · Nicolas Vecoven, Damien Ernst, Guillaume Drion

Recurrent neural networks (RNNs) provide state-of-the-art performances in a wide variety of tasks that require memory. These performances can often be achieved thanks to gated recurrent cells such as gated recurrent unit…

Time Series Analysis

Recurrent Dropout without Memory Loss

2016-03-16 · COLING 2016 12 · Stanislau Semeniuta, Aliaksei Severyn, Erhardt Barth

This paper presents a novel approach to recurrent neural network (RNN) regularization. Differently from the widely adopted dropout method, which is applied to \textit{forward} connections of feed-forward architectures or…

High Order Recurrent Neural Networks for Acoustic Modelling

2018-02-22 · Chao Zhang, Philip Woodland

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters asso…

Acoustic Modellingspeech-recognitionSpeech RecognitionVocal Bursts Intensity Prediction

Dilated Recurrent Neural Networks

2017-10-05 · NeurIPS 2017 12 · Shiyu Chang, Yang Zhang, Wei Han, Mo Yu 외

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallel…

Sequential Image Classification

Dropout improves Recurrent Neural Networks for Handwriting Recognition

2013-11-05 · Vu Pham, Théodore Bluche, Christopher Kermorvant, Jérôme Louradour

Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a …

Handwriting Recognition