2 papers
cs.LG2023
Universal Recurrent Event Memories for Streaming Data
Ran Dou, Jose Principe
In this paper, we propose a new event memory architecture (MemNet) for recurrent neural networks, which is universal for different types of time series data such as scalar, multiva…
cs.LG2023
Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks
Ran Dou, Jose Principe
In recurrent neural networks, learning long-term dependency is the main difficulty due to the vanishing and exploding gradient problem. Many researchers are dedicated to solving th…