Related papers: SOI: Scaling Down Computational Complexity by Esti…

The adoption of intelligent systems with Artificial Neural Networks (ANNs) embedded in hardware for real-time applications currently faces a growing demand in fields like the Internet of Things (IoT) and Machine to Machine (M2M). However,…

Spiking Neural Networks (SNNs) have emerged as a promising substitute for Artificial Neural Networks (ANNs) due to their advantages of fast inference and low power consumption. However, the lack of efficient training algorithms has hindered…

In split inference, a deep neural network (DNN) is partitioned to run the early part of the DNN at the edge and the later part of the DNN in the cloud. This meets two key requirements for on-device machine learning: input privacy and…

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the…

On-device computing, or edge computing, is becoming increasingly important for remote sensing, particularly in applications like deep network-based perception on on-orbit satellites and unmanned aerial vehicles (UAVs). In these scenarios,…

Neuromorphic computing and, in particular, spiking neural networks (SNNs) have become an attractive alternative to deep neural networks for a broad range of signal processing applications, processing static and/or temporal inputs from…

As neural networks get widespread adoption in resource-constrained embedded devices, there is a growing need for low-power neural systems. Spiking Neural Networks (SNNs)are emerging to be an energy-efficient alternative to the traditional…

Spiking Neural Networks (SNNs) can achieve competitive performance by converting already existing well-trained Artificial Neural Networks (ANNs), avoiding further costly training. This property is particularly attractive in Reinforcement…

Artificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a…

Applying large language models (LLMs) for academic API usage shows promise in reducing researchers' academic information seeking efforts. However, current LLM API-using methods struggle with complex API coupling commonly encountered in…

Batch training of machine learning models based on neural networks is now well established, whereas to date streaming methods are largely based on linear models. To go beyond linear in the online setting, nonparametric methods are of…

Model compression has emerged as an important area of research for deploying deep learning models on Internet-of-Things (IoT). However, for extremely memory-constrained scenarios, even the compressed models cannot fit within the memory of a…

In this paper, we infer remote measurements such as remote voltages and currents online with change in AC power flows using spiking neural network (SNN) as grid-edge technology for efficient coordination of power electronic converters. This…

Making material experiments more efficient is a high priority for materials scientists who seek to discover new materials with desirable properties. In this paper, we investigate how to optimize the laborious sequential measurements of…

Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation,…

The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying…

We consider a node where packets of fixed size (in bits) are generated at arbitrary intervals. The node is required to maintain the peak age of information (AoI) at the monitor below a threshold by transmitting potentially a subset of the…

Herein, a bit-wise Convolutional Neural Network (CNN) in-memory accelerator is implemented using Spin-Orbit Torque Magnetic Random Access Memory (SOT-MRAM) computational sub-arrays. It utilizes a novel AND-Accumulation method capable of…

Applications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time…

The majority of IoT devices like smartwatches, smart plugs, HVAC controllers, etc., are powered by hardware with a constrained specification (low memory, clock speed and processor) which is insufficient to accommodate and execute large,…