LGMLApr 18, 2018

Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks

arXiv:1804.06776v119 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of long-horizon forecasting for applications like neuroscience and energy management, though it appears incremental as it builds on existing LSTM and Dynamic Belief Networks literature.

The paper tackles the problem of performance decay in long-horizon forecasting with LSTM networks by proposing expectation-biasing, which significantly outperforms standard methods in neuroscience and energy supply management datasets.

State-of-the-art forecasting methods using Recurrent Neural Net- works (RNN) based on Long-Short Term Memory (LSTM) cells have shown exceptional performance targeting short-horizon forecasts, e.g given a set of predictor features, forecast a target value for the next few time steps in the future. However, in many applica- tions, the performance of these methods decays as the forecasting horizon extends beyond these few time steps. This paper aims to explore the challenges of long-horizon forecasting using LSTM networks. Here, we illustrate the long-horizon forecasting problem in datasets from neuroscience and energy supply management. We then propose expectation-biasing, an approach motivated by the literature of Dynamic Belief Networks, as a solution to improve long-horizon forecasting using LSTMs. We propose two LSTM ar- chitectures along with two methods for expectation biasing that significantly outperforms standard practice.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes