A proper parametrization of state transition matrices of linear state-space models (SSMs)
followed by standard nonlinearities enables them to efficiently learn representations from …

Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for
modeling irregularly-sampled time series. These models, however, face difficulties when the …

With the rapid development of information technology, image and text data have increased
dramatically. Image and text matching techniques enable computers to understand …

The proliferation of new technologies and advancements in existing ones are altering our
perspective of the world. So, continuous improvements are needed. A connected world filled …

We present a novel learning framework to obtain finite-state controllers (FSCs) for partially
observable Markov decision processes and illustrate its applicability for indefinite-horizon …

Predicting volatility is a critical activity for taking risk-adjusted decisions in asset trading and
allocation. In order to provide effective decision-making support, in this paper we investigate …

Deep learning has achieved great successes in many important areas to dealing with text,
images, video, graphs, and so on. However, the black-box nature of deep artificial neural …

We present a method to extract a weighted finite automaton (WFA) from a recurrent neural
network (RNN). Our method is based on the WFA learning algorithm by Balle and Mohri …

Transformers are state-of-the-art in a wide range of NLP tasks and have also been applied
to many real-world products. Understanding the reliability and certainty of transformer …

Artificial neural networks (ANNs) with recurrence and self-attention have been shown to be
Turing-complete (TC). However, existing work has shown that these ANNs require multiple …