On a novel training algorithm for sequence-to-sequence predictive recurrent networks
원문 초록
Neural networks mapping sequences to sequences (seq2seq) lead to significant progress in machine translation and speech recognition. Their traditional architecture includes two recurrent networks (RNs) followed by a linear predictor. In this manuscript we perform analysis of a corresponding algorithm and show that the parameters of the RNs of the well trained predictive network are not independent of each other. Their dependence can be used to significantly improve the network effectiveness. The traditional seq2seq algorithms require short term memory of a size proportional to the predicted sequence length. This requirement is quite difficult to implement in a neuroscience context. We present a novel memoryless algorithm for seq2seq predictive networks and compare it to the traditional one in the context of time series prediction. We show that the new algorithm is more robust and makes predictions with higher accuracy than the traditional one.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Robust Online Time Series Prediction with Recurrent Neural Networks
A Review of the Long Horizon Forecasting Problem in Time Series Analysis
The interplay of robustness and generalization in quantum machine learning
A Better Alternative to Piecewise Linear Time Series Segmentation
Predicting Graph Structure via Adapted Flux Balance Analysis
Process mining-driven modeling and simulation to enhance fault diagnosis in cyber-physical systems
토론
이 논문과 연결된 포럼 글이 아직 없습니다.