Richard Lau

Richard Lau, Anthony Tylan-Tyler, Lihan Yao et al.

This paper describes a temporal-spatial model for video processing with special applications to processing event camera videos. We propose to study a conjecture motivated by our previous study of video processing with delay loop reservoir (DLR) neural network, which we call Temporal-Spatial Conjecture (TSC). The TSC postulates that there is significant information content carried in the temporal representation of a video signal and that machine learning algorithms would benefit from separate optimization of the spatial and temporal components for intelligent processing. To verify or refute the TSC, we propose a Visual Markov Model (VMM) which decompose the video into spatial and temporal components and estimate the mutual information (MI) of these components. Since computation of video mutual information is complex and time consuming, we use a Mutual Information Neural Network to estimate the bounds of the mutual information. Our result shows that the temporal component carries significant MI compared to that of the spatial component. This finding has often been overlooked in neural network literature. In this paper, we will exploit this new finding to guide our design of a delay-loop reservoir neural network for event camera classification, which results in a 18% improvement on classification accuracy.

Richard Lau, Lihan Yao, Todd Huster et al.

This paper describes a systematic approach towards building a new family of neural networks based on a delay-loop version of a reservoir neural network. The resulting architecture, called Scaled-Time-Attention Robust Edge (STARE) network, exploits hyper dimensional space and non-multiply-and-add computation to achieve a simpler architecture, which has shallow layers, is simple to train, and is better suited for Edge applications, such as Internet of Things (IoT), over traditional deep neural networks. STARE incorporates new AI concepts such as Attention and Context, and is best suited for temporal feature extraction and classification. We demonstrate that STARE is applicable to a variety of applications with improved performance and lower implementation complexity. In particular, we showed a novel way of applying a dual-loop configuration to detection and identification of drone vs bird in a counter Unmanned Air Systems (UAS) detection application by exploiting both spatial (video frame) and temporal (trajectory) information. We also demonstrated that the STARE performance approaches that of a State-of-the-Art deep neural network in classifying RF modulations, and outperforms Long Short-term Memory (LSTM) in a special case of Mackey Glass time series prediction. To demonstrate hardware efficiency, we designed and developed an FPGA implementation of the STARE algorithm to demonstrate its low-power and high-throughput operations. In addition, we illustrate an efficient structure for integrating a massively parallel implementation of the STARE algorithm for ASIC implementation.