Related papers: All-in-One: A Highly Representative DNN Pruning Fr…

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…

Automated feature extraction capability and significant performance of Deep Neural Networks (DNN) make them suitable for Internet of Things (IoT) applications. However, deploying DNN on edge devices becomes prohibitive due to the colossal…

Deep neural networks (DNNs) have showcased remarkable performance across various tasks and are widely deployed on AI accelerators fabricated in advanced technology nodes for efficiency. As aging effects become more pronounced, timing and…

Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an…

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…

Modern Deep Neural Networks (DNNs) exhibit profound efficiency and accuracy properties. This has introduced application workloads that comprise of multiple DNN applications, raising new challenges regarding workload distribution. Equipped…

Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with advances in deep neural networks (DNNs), have opened up new opportunities for enabling sustainable smart applications. Nevertheless, implementing…

Deep neural network (DNN) inference in energy harvesting (EH) devices poses significant challenges due to resource constraints and frequent power interruptions. These power losses not only increase end-to-end latency, but also compromise…

The state-of-art DNN structures involve intensive computation and high memory storage. To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework…

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-trivial to deploy…

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…

The rise of mobile AI accelerators allows latency-sensitive applications to execute lightweight Deep Neural Networks (DNNs) on the client side. However, critical applications require powerful models that edge devices cannot host and must…

While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip…

DNN pruning is a popular way to reduce the size of a model, improve the inference latency, and minimize the power consumption on DNN accelerators. However, existing approaches might be too complex, expensive or ineffective to apply to a…

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

The increasing usage of Artificial Intelligence (AI) models, especially Deep Neural Networks (DNNs), is increasing the power consumption during training and inference, posing environmental concerns and driving the need for more…

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g.,…

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…

In recent years there has been an increasing use of embedded systems because of advances in technology, the reduction of the costs of electronic equipment and mainly the popularity of mobile devices. Many of these systems implement low…