Related papers: LASANA: Large-Scale Surrogate Modeling for Analog …

Spiking Neural Networks (SNNs) offer a biologically inspired alternative to conventional artificial neural networks, with potential advantages in power efficiency due to their event-driven computation. Despite their promise, SNNs have yet…

Artificial intelligence and machine learning models deployed on edge devices, e.g., for quality control in Additive Manufacturing (AM), are frequently small in size. Such models usually have to deliver highly accurate results within a short…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs). However, it remains an open problem, how to integrate NAS…

Developing accurate, data-efficient surrogate models is central to advancing AI for Science. Neural operators (NOs), which approximate mappings between infinite-dimensional function spaces using conventional neural architectures, have…

We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of…

Spiking Neural Networks (SNNs), particularly Spiking Transformers, offer energy-efficient processing of event-based sensor data for healthcare applications. Yet current architectures are rigid: they are trained and deployed as static…

Deep 'Analog Artificial Neural Networks' (ANNs) perform complex classification problems with remarkably high accuracy. However, they rely on humongous amount of power to perform the calculations, veiling the accuracy benefits. The…

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM)…

Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods like linear attention, existing SP approaches do not take…

Machine learning has emerged as the dominant tool for implementing complex cognitive tasks that require supervised, unsupervised, and reinforcement learning. While the resulting machines have demonstrated in some cases even super-human…

Computation using brain-inspired spiking neural networks (SNNs) with neuromorphic hardware may offer orders of magnitude higher energy efficiency compared to the current analog neural networks (ANNs). Unfortunately, training SNNs with the…

Reinforcement learning (RL)-based neural architecture search (NAS) generally guarantees better convergence yet suffers from the requirement of huge computational resources compared with gradient-based approaches, due to the rollout…

Emerging ReRAM-based accelerators process neural networks via analog Computing-in-Memory (CiM) for ultra-high energy efficiency. However, significant overhead in peripheral circuits and complex nonlinear activation modes constrain system…

Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, offer a distinctive approach for capturing the complexities of temporal data. However, their potential for spatial modeling in multivariate time-series…

Cryogenic neuromorphic systems, inspired by the brains unparalleled efficiency, present a promising paradigm for next generation computing architectures.This work introduces a fully integrated neuromorphic framework that combines…

Spiking Neural Networks (SNNs) are extensively utilized in brain-inspired computing and neuroscience research. To enhance the speed and energy efficiency of SNNs, several many-core accelerators have been developed. However, maintaining the…

The Dragonfly network, with its high-radix and low-diameter structure, is a leading interconnect in high-performance computing. A major challenge is workload interference on shared network links. Parallel discrete event simulation (PDES) is…

Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can…

We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure and…