相关论文: Efficient Post-Training Augmentation for Adaptive …

Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains. Nevertheless, a common issue…

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low power consumption and improve the efficiency of these models…

Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill…

Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy inputs while retaining full-depth accuracy on harder ones. Similarly, adding early exit mechanisms to…

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the…

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the…

Many real-time applications (e.g., Augmented/Virtual Reality, cognitive assistance) rely on Deep Neural Networks (DNNs) to process inference tasks. Edge computing is considered a key infrastructure to deploy such applications, as moving…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The two major types are Long Short-Term Memory (LSTM) and Gated Recurrent Unit…

Single-channel speech enhancement algorithms are often used in resource-constrained embedded devices, where low latency and low complexity designs gain more importance. In recent years, researchers have proposed a wide variety of novel…

Neural Architecture Search (NAS) has received increasing attention because of its exceptional merits in automating the design of Deep Neural Network (DNN) architectures. However, the performance evaluation process, as a key part of NAS,…

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and…

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redundancy in network depth or width. In this paper, we focus on…

Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices. Recently, there have been greater efforts in the design…

Deep neural networks achieve outstanding results in challenging image classification tasks. However, the design of network topologies is a complex task and the research community makes a constant effort in discovering top-accuracy…

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets.…

The continued need for improvements in accuracy, throughput, and efficiency of Deep Neural Networks has resulted in a multitude of methods that make the most of custom architectures on FPGAs. These include the creation of hand-crafted…

It is a widely accepted fact that data representations intervene noticeably in machine learning tools. The more they are well defined the better the performance results are. Feature extraction-based methods such as autoencoders are…

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…

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…