Related papers: Walle: An End-to-End, General-Purpose, and Large-S…

Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight…

The smart devices are extremely useful devices that are making our lives easier than before. A smart device is facilitated us to establish a connection with another smart device in a wireless network with a decentralized approach. The…

Physical neural networks (PNNs) embed computation directly in material dynamics, including molecular, chemical, biological, photonic, memristive, and mechanical substrates. They are attractive for edge computing, especially at the extreme…

Deep Neural Networks (DNNs) have drawn attention because of their outstanding performance on various tasks. However, deploying full-fledged DNNs in resource-constrained devices (edge, mobile, IoT) is difficult due to their large size. To…

Machine learning (ML) applications become increasingly common in many domains. ML systems to execute these workloads include numerical computing frameworks and libraries, ML algorithm libraries, and specialized systems for deep neural…

In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to DNN partitioning and offloading across the edge-cloud continuum typically rely on static…

We present a versatile open-source framework designed to facilitate efficient, numerically-tailored Matrix-Matrix Multiplications (MMMs). The framework offers two primary contributions: first, a fine-tuned, automated pipeline for arithmetic…

This paper proposes a fully decentralized federated learning (FL) scheme for Internet of Everything (IoE) devices that are connected via multi-hop networks. Because FL algorithms hardly converge the parameters of machine learning (ML)…

Multi-task large language models (MTLLMs) are important for many applications at the wireless edge, where users demand specialized models to handle multiple tasks efficiently. However, training MTLLMs is complex and exhaustive, particularly…

Machine intelligence, especially using convolutional neural networks (CNNs), has become a large area of research over the past years. Increasingly sophisticated hardware accelerators are proposed that exploit e.g. the sparsity in…

With the surge of inexpensive computational and memory resources, neural networks (NNs) have experienced an unprecedented growth in architectural and computational complexity. Introducing NNs to resource-constrained devices enables…

We reinvigorate maximum likelihood estimation (MLE) for macroeconomic density forecasting through a novel neural network architecture with dedicated mean and variance hemispheres. Our architecture features several key ingredients making MLE…

Existing distributed machine learning (DML) systems focus on improving the computational efficiency of distributed learning, whereas communication aspects have received less attention. Many DML systems treat the network as a blackbox. Thus,…

This article provides an overview of the Collective Knowledge technology (CK or cKnowledge). CK attempts to make it easier to reproduce ML&systems research, deploy ML models in production, and adapt them to continuously changing data sets,…

Deep Neural Networks (DNNs) have transformed the field of machine learning and are widely deployed in many applications involving image, video, speech and natural language processing. The increasing compute demands of DNNs have been widely…

We describe a new software framework for fast training of generalized linear models. The framework, named Snap Machine Learning (Snap ML), combines recent advances in machine learning systems and algorithms in a nested manner to reflect the…

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…

While existing machine learning (ML) frameworks focus on established platforms, like running CUDA on server-grade GPUs, there have been growing demands to enable emerging AI applications in a broader set of scenarios, such as running Large…

Recent years have seen the emergence of machine learning (ML) workloads deployed in warehouse-scale computing (WSC) settings, also known as ML fleets. As the computational demands placed on ML fleets have increased due to the rise of large…

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…