Related papers: Memory-efficient Energy-adaptive Inference of Pre-…

Pervasive AI increasingly depends on on-device learning systems that deliver low-latency and energy-efficient computation under strict resource constraints. Liquid State Machines (LSMs) offer a promising approach for low-power temporal…

The field of Tiny Machine Learning (TinyML) has gained significant attention due to its potential to enable intelligent applications on resource-constrained devices. This review provides an in-depth analysis of the advancements in efficient…

The use of Dynamic Random Access Memory (DRAM) for storing Machine Learning (ML) models plays a critical role in accelerating ML inference tasks in the next generation of communication systems. However, periodic refreshment of DRAM results…

In recent years, the proliferation of unmanned aerial vehicles (UAVs) has increased dramatically. UAVs can accomplish complex or dangerous tasks in a reliable and cost-effective way but are still limited by power consumption problems, which…

Increasingly complex neural network architectures have achieved phenomenal performance. However, these complex models require massive computational resources that consume substantial amounts of electricity, which highlights the potential…

Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they…

Deep Neural Network (DNN) based inference at the edge is challenging as these compute and data-intensive algorithms need to be implemented at low cost and low power while meeting the latency constraints of the target applications. Sparsity,…

Large Language Models (LLMs) have fundamentally altered how we approach scaling in machine learning. However, these models pose substantial computational and memory challenges, primarily due to the reliance on matrix multiplication (MatMul)…

The implicit solvent approach offers a computationally efficient framework to model solvation effects in molecular simulations. However, its accuracy often falls short compared to explicit solvent models, limiting its use in precise…

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models are held in memory. Model compression methods address this…

Emerging research in edge devices and micro-controller units (MCU) enables on-device computation of Deep Learning Training and Inferencing tasks. More recently, contemporary trends focus on making the Deep Neural Net (DNN) Models runnable…

A new algorithm for incremental learning in the context of Tiny Machine learning (TinyML) is presented, which is optimized for low-performance and energy efficient embedded devices. TinyML is an emerging field that deploys machine learning…

Transformer-based models with the pretrain-finetune paradigm bring about significant progress, along with the heavy storage and deployment costs of finetuned models on multiple tasks. Delta compression attempts to lower the costs by…

Sensing systems powered by energy harvesting have traditionally been designed to tolerate long periods without energy. As the Internet of Things (IoT) evolves towards a more transient and opportunistic execution paradigm, reducing energy…

The performance of neural networks improves when more parameters are used. However, the model sizes are constrained by the available on-device memory during training and inference. Although applying techniques like quantization can…

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

As power systems are undergoing a significant transformation with more uncertainties, less inertia and closer to operation limits, there is increasing risk of large outages. Thus, there is an imperative need to enhance grid emergency…