4 papers
MagNet: Discovering Multi-agent Interaction Dynamics using Neural Network
Priyabrata Saha, Arslan Ali, Burhan A. Mudassar +2
We present the MagNet, a neural network-based multi-agent interaction model to discover the governing dynamics and predict evolution of a complex multi-agent system from observatio…
Improving Robustness of ReRAM-based Spiking Neural Network Accelerator with Stochastic Spike-timing-dependent-plasticity
Xueyuan She, Yun Long, Saibal Mukhopadhyay
Spike-timing-dependent-plasticity (STDP) is an unsupervised learning algorithm for spiking neural network (SNN), which promises to achieve deeper understanding of human brain and m…
ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction
Xueyuan She, Yun Long, Daehyun Kim +1
Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the…
HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
Yun Long, Xueyuan She, Saibal Mukhopadhyay
The robotic systems continuously interact with complex dynamical systems in the physical world. Reliable predictions of spatiotemporal evolution of these dynamical systems, with li…