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

Human Activity Recognition (HAR) is critical for applications in healthcare, fitness, and IoT, but deploying accurate models on resource-constrained devices remains challenging due to high energy and memory demands. This paper demonstrates…

This article proposes a model-based deep reinforcement learning (DRL) method to design emergency control strategies for short-term voltage stability problems in power systems. Recent advances show promising results in model-free DRL-based…

State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computational cost. Light-weight architectures, on the other hand,…

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…

Memory optimization for deep neural network (DNN) inference gains high relevance with the emergence of TinyML, which refers to the deployment of DNN inference tasks on tiny, low-power microcontrollers. Applications such as audio keyword…

Many DNN-enabled vision applications constantly operate under severe energy constraints such as unmanned aerial vehicles, Augmented Reality headsets, and smartphones. Designing DNNs that can meet a stringent energy budget is becoming…

The increasing deployment of large language models (LLMs) in natural language processing (NLP) tasks raises concerns about energy efficiency and sustainability. While prior research has largely focused on energy consumption during model…

The rapid growth of deep neural networks (DNNs) has brought increasing attention to their energy use during training and inference. Here, we establish the thermodynamic bounds on energy consumption in quasi-static analog DNNs by mapping…

The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such…

Despite rapid advancements, machine learning, particularly deep learning, is hindered by the need for large amounts of labeled data to learn meaningful patterns without overfitting and immense demands for computation and storage, which…

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,…

Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted…

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…

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…

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully…

Training deep neural networks (DNNs) directly on edge devices has attracted increasing attention, as it offers promising solutions to challenges such as domain adaptation and privacy preservation. However, conventional DNN training…

Artificial intelligence (AI) has enabled a new paradigm of smart applications -- changing our way of living entirely. Many of these AI-enabled applications have very stringent latency requirements, especially for applications on mobile…

Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantization reduce per-parameter cost, transformer-based models remain too large for the 3.3-7.4…

Frugal Machine Learning (FML) refers to the practice of designing Machine Learning (ML) models that are efficient, cost-effective, and mindful of resource constraints. This field aims to achieve acceptable performance while minimizing the…

Reducing inference time and energy usage while maintaining prediction accuracy has become a significant concern for deep neural networks (DNN) inference on resource-constrained edge devices. To address this problem, we propose a novel…