Related papers: DeepRebirth: Accelerating Deep Neural Network Exec…

Network slicing is a key technique in 5G and beyond for efficiently supporting diverse services. Many network slicing solutions rely on deep learning to manage complex and high-dimensional resource allocation problems. However, deep…

To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a…

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

Artificial intelligence have contributed to advancements across various industries. However, the rapid growth of artificial intelligence technologies also raises concerns about their environmental impact, due to associated carbon footprints…

Automatic RF modulation recognition is a primary signal intelligence (SIGINT) technique that serves as a physical layer authentication enabler and automated signal processing scheme for the beyond 5G and military networks. Most existing…

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

The non-uniform sampling is a powerful approach to enable fast acquisition but requires sophisticated reconstruction algorithms. Faithful reconstruction from partial sampled exponentials is highly expected in general signal processing and…

Existing high-performance deep learning models require very intensive computing. For this reason, it is difficult to embed a deep learning model into a system with limited resources. In this paper, we propose the novel idea of the network…

As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.…

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into…

This work focuses on reducing neural network size, which is a major driver of neural network execution time, power consumption, bandwidth, and memory footprint. A key challenge is to reduce size in a manner that can be exploited readily for…

Deep neural speech and audio processing systems have a large number of trainable parameters, a relatively complex architecture, and require a vast amount of training data and computational power. These constraints make it more challenging…

Recently, image enhancement and restoration have become important applications on mobile devices, such as super-resolution and image deblurring. However, most state-of-the-art networks present extremely high computational complexity. This…

Performance is a critical challenge in mobile image processing. Given a reference imaging pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements and enable real-time evaluation. For this, we introduce a new…

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Neural network deployment on low-cost embedded systems, hence on microcontrollers (MCUs), has recently been attracting more attention than ever. Since MCUs have limited memory capacity as well as limited compute-speed, it is critical that…

Energy use is a key concern when deploying deep learning models on mobile and embedded platforms. Current studies develop energy predictive models based on application-level features to provide researchers a way to estimate the energy…

Achieving faster execution with shorter compilation time can foster further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional…