Quantized Approximately Orthogonal Recurrent Neural Networks

Orthogonal recurrent neural networks (ORNNs) are an appealing option for learning tasks involving time series with long-term dependencies, thanks to their simplicity and computational stability. However, these networks often require a substantial number of parameters to perform well, which can be prohibitive in power-constrained environments, such as compact devices. One approach to address this issue is neural network quantization. The construction of such networks remains an open problem, acknowledged for its inherent instability.In this paper, we explore the quantization of …

computational cs.lg cs.ne dependencies devices eess.sp environments long-term math.st networks neural networks parameters power recurrent neural networks series simplicity stability stat.th tasks time series