Online learning with recurrent neural networks
Embargo Lift Date: 2021-07-17
Item Usage Stats
In this thesis, we study online learning with Recurrent Neural Networks (RNNs). Particularly, in Chapter 2, we investigate online nonlinear regression and introduce novel regression structures based on the Long Short Term Memory (LSTM) network, i.e., is an advanced RNN architecture. To train these novel LSTM based structures, we introduce highly e cient and e ective Particle Filtering (PF) based updates. We also provide Stochastic Gradient Descent (SGD) and Extended Kalman Filter (EKF) based updates. Our PF based training method guarantees convergence to the optimal parameter estimation in the Mean Square Error (MSE) sense. In Chapter 3, we investigate online training of LSTM architectures in a distributed network of nodes, where each node employs an LSTM based structure for online regression. We rst provide a generic LSTM based regression structure for each node. In order to train this structure, we introduce a highly e ective and e cient Distributed PF (DPF) based training algorithm. We also introduce a Distributed EKF (DEKF) based training algorithm. Here, our DPF based training algorithm guarantees convergence to the performance of the optimal centralized LSTM parameters in the MSE sense. In Chapter 4, we investigate variable length data regression in an online setting and introduce an energy e cient regression structure build on LSTM networks. To reduce the complexity of this structure, we rst replace the regular multiplication operations with an energy e cient operator. We then apply factorizations to the weight matrices so that the total number of parameters to be trained is signi cantly reduced. We then introduce online training algorithms. Through a set of experiments, we illustrate signi cant performance gains and complexity reductions achieved by the introduced algorithms with respect to the state of the art methods.
Recurrent Neural Network (RNN)
Extended Kalman ltering (EKF)
Particle ltering (PF)
Stochastic Gradient Descent (SGD)