相关论文: Intermittent Inference with Nonuniformly Compresse…

The success of deep learning has been due, in no small part, to the availability of large annotated datasets. Thus, a major bottleneck in current learning pipelines is the time-consuming human annotation of data. In scenarios where such…

In this paper, we consider a multiple-input multiple-output wireless powered communication network (MIMO-WPCN), where multiple users harvest energy from a dedicated power station in order to be able to transmit their information signals to…

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…

For many practical applications, a high computational cost of inference over deep network architectures might be unacceptable. A small degradation in the overall inference accuracy might be a reasonable price to pay for a significant…

Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often overlooked, possibly due to a lack of sustainability mindset…

Early Exit (EE) techniques have emerged as a means to reduce inference latency in Deep Neural Networks (DNNs). The latency improvement and accuracy in these techniques crucially depend on the criteria used to make exit decisions. We propose…

Currently, the world experiences an unprecedentedly increasing generation of application data, from sensor measurements to video streams, thanks to the extreme connectivity capability provided by 5G networks. Going beyond 5G technology,…

Deep learning, as a highly efficient method for metasurface inverse design, commonly use simulation data to train deep neural networks (DNNs) that can map desired functionalities to proper metasurface designs. However, the assumptions and…

Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload…

Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g., the total number of weights/operations) while maintaining a…

Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak…

Recent years have seen a paradigm shift towards multi-task learning. This calls for memory and energy-efficient solutions for inference in a multi-task scenario. We propose an algorithm-hardware co-design approach called MIME. MIME reuses…

We consider an energy harvesting (EH) multi-antenna relay based cooperative cognitive radio network (CCRN), and investigate its outage and throughput performance with the peak-interference type of power control for both time-switching (TS)…

This paper proposes a hardware-oriented dropout algorithm, which is efficient for field programmable gate array (FPGA) implementation. In deep neural networks (DNNs), overfitting occurs when networks are overtrained and adapt too well to…

Deep learning algorithms have shown tremendous success in many recognition tasks; however, these algorithms typically include a deep neural network (DNN) structure and a large number of parameters, which makes it challenging to implement…

The inherent diversity of computation types within the deep neural network (DNN) models often requires a variety of specialized units in hardware processors, which limits computational efficiency, increasing both inference latency and power…

Electricity is a volatile power source that requires great planning and resource management for both short and long term. More specifically, in the short-term, accurate instant energy consumption forecasting contributes greatly to improve…

Deep neural networks (DNNs) have succeeded in many different perception tasks, e.g., computer vision, natural language processing, reinforcement learning, etc. The high-performed DNNs heavily rely on intensive resource consumption. For…

There is an increasing demand for intelligent processing on emerging ultra-low-power internet of things (IoT) devices, and recent works have shown substantial efficiency boosts by executing inference tasks directly on the IoT device (node)…

Deep neural networks (DNNs) have been widely applied in diverse applications, but the problems of high latency and energy overhead are inevitable on resource-constrained devices. To address this challenge, most researchers focus on the…