Initializing LSTM internal states via manifold learning

Abstract

We present an approach, based on learning an intrinsic data manifold, for the initialization of the internal state values of LSTM recurrent neural networks, ensuring consistency with the initial observed input data. Exploiting the generalized synchronization concept, we argue that the converged, "mature" internal states constitute a function on this learned manifold. The dimension of this manifold then dictates the length of observed input time series data required for consistent initialization. We illustrate our approach through a partially observed chemical model system, where initializing the internal LSTM states in this fashion yields visibly improved performance. Finally, we show that learning this data manifold enables the transformation of partially observed dynamics into fully observed ones, facilitating alternative identification paths for nonlinear dynamical systems.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• LSTM: A Search Space Odyssey
• On the difficulty of training Recurrent Neural Networks
• Recent Advances in Physical Reservoir Computing: A Review
• Recent Advances in Recurrent Neural Networks
• Attractor Reconstruction by Machine Learning
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• Controlling Recurrent Neural Networks by Conceptors