Related papers: A synchronization-capturing multi-scale solver to …
Spiking Neural Networks (SNNs) are capable of encoding and processing temporal information in a biologically plausible way. However, most existing SNN-based methods for image tasks do not fully exploit this feature. Moreover, they often…
Deciding the amount of neurons during the design of a deep neural network to maximize performance is not intuitive. In this work, we attempt to search for the neuron (filter) configuration of a fixed network architecture that maximizes…
Missing values, irregularly collected samples, and multi-resolution signals commonly occur in multivariate time series data, making predictive tasks difficult. These challenges are especially prevalent in the healthcare domain, where…
Finding informative low-dimensional descriptions of high-dimensional simulation data (like the ones arising in molecular dynamics or kinetic Monte Carlo simulations of physical and chemical processes) is crucial to understanding physical…
In this paper, we investigate neural networks applied to multiscale simulations and discuss a design of a novel deep neural network model reduction approach for multiscale problems. Due to the multiscale nature of the medium, the fine-grid…
As computing resource demands continue to escalate in the face of big data, cloud-connectivity and the internet of things, it has become imperative to develop new low-power, scalable architectures. Neuromorphic photonics, or photonic neural…
Recently, a multi-level fuzzy min max neural network (MLF) was proposed, which improves the classification accuracy by handling an overlapped region (area of confusion) with the help of a tree structure. In this brief, an extension of MLF…
Spiking neural networks (SNN) are able to learn spatiotemporal features while using less energy, especially on neuromorphic hardware. The most widely used spiking neuron in deep learning is the Leaky Integrate and Fire (LIF) neuron. LIF…
Spiking neural networks (SNNs) present a promising computing paradigm for neuromorphic processing of event-based sensor data. The resonate-and-fire (RF) neuron, in particular, appeals through its biological plausibility, complex dynamics,…
Recently, low-dimensional models of neuronal activity have been exactly derived for large networks of deterministic, Quadratic Integrate-and-Fire (QIF) neurons. Such firing rate models (FRM) describe the emergence of fast collective…
Mixed Integer Programming (MIP) solvers rely on an array of sophisticated heuristics developed with decades of research to solve large-scale MIP instances encountered in practice. Machine learning offers to automatically construct better…
Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically…
The escalating energy demands of artificial intelligence pose a critical challenge to conventional computing. Leveraging the efficiency of event-driven, in-memory neuromorphic architectures into the superconducting circuits with ultra-high…
We present a SNN simulator which scales to millions of neurons, billions of synapses, and 8 GPUs. This is made possible by 1) a novel, cache-aware spike transmission algorithm 2) a model parallel multi-GPU distribution scheme and 3) a…
Spiking neural networks (SNN) provide a new computational paradigm capable of highly parallelized, real-time processing. Photonic devices are ideal for the design of high-bandwidth, parallel architectures matching the SNN computational…
Spiking Neural Networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multi-scale temporal processing compared to their biological…
Neuromorphic computing leveraging spiking neural network has emerged as a promising solution to tackle the security and reliability challenges with the conventional cyber-physical infrastructure of microgrids. Its event-driven paradigm…
We propose a Neural-Enhanced Distributed Kalman Filter (NDKF) for multi-sensor state estimation in nonlinear systems. Unlike traditional Kalman filters that rely on explicit analytical models and assume centralized fusion, NDKF leverages…
The computational complexity of deep learning algorithms has given rise to significant speed and memory challenges for the execution hardware. In energy-limited portable devices, highly efficient processing platforms are indispensable for…
The human brain exhibits remarkable abilities in integrating temporally distant sensory inputs for decision-making. However, existing brain-inspired spiking neural networks (SNNs) have struggled to match their biological counterpart in…