Related papers: Accelerate Intermittent Deep Inference

The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these…

Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications cause expensive resource costs that challenge DNNs' deployment on resource-constrained edge devices,…

Deep Neural Networks (DNNs) have been established as the state-of-the-art algorithm for advanced machine learning applications. Recently, CapsuleNets have improved the generalization ability, as compared to DNNs, due to their…

Edge intelligence enables resource-demanding Deep Neural Network (DNN) inference without transferring original data, addressing concerns about data privacy in consumer Internet of Things (IoT) devices. For privacy-sensitive applications,…

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives…

Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly…

The rapid advancement of deep learning has catalyzed the development of novel IoT applications, which often deploy pre-trained deep neural network (DNN) models across multiple edge devices for collaborative inference.

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

Early-exit networks are effective solutions for reducing the overall energy consumption and latency of deep learning models by adjusting computation based on the complexity of input data. By incorporating intermediate exit branches into the…

Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…

Neural networks often encounter various stringent resource constraints while deploying on edge devices. To tackle these problems with less human efforts, automated machine learning becomes popular in finding various neural architectures…

Specialized compute blocks have been developed for efficient DNN execution. However, due to the vast amount of data and parameter movements, the interconnects and on-chip memories form another bottleneck, impairing power and performance.…

Computing at the edge is increasingly important since a massive amount of data is generated. This poses challenges in transporting all that data to the remote data centers and cloud, where they can be processed and analyzed. On the other…

The recent ground-breaking advances in deep learning networks ( DNNs ) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the…

Training deep neural networks (DNNs) on edge devices has attracted increasing attention due to its potential to address challenges related to domain adaptation and privacy preservation. However, DNNs typically rely on large datasets for…

Deep neural networks (DNNs) are state-of-the-art solutions for many machine learning applications, and have been widely used on mobile devices. Running DNNs on resource-constrained mobile devices often requires the help from edge servers…

Neural networks (NNs) with intensive multiplications (e.g., convolutions and transformers) are capable yet power hungry, impeding their more extensive deployment into resource-constrained devices. As such, multiplication-free networks,…

A surge in artificial intelligence and autonomous technologies have increased the demand toward enhanced edge-processing capabilities. Computational complexity and size of state-of-the-art Deep Neural Networks (DNNs) are rising…

The ability to accurately predict deep neural network (DNN) inference performance metrics, such as latency, power, and memory footprint, for an arbitrary DNN on a target hardware platform is essential to the design of DNN based models. This…

Designing deep networks that meet strict latency and accuracy constraints on edge accelerators increasingly relies on hardware-aware optimization, including neural architecture search (NAS) guided by device-level metrics. Yet most…