Related papers: In-network Neural Networks
With the surging popularity of edge computing, the need to efficiently perform neural network inference on battery-constrained IoT devices has greatly increased. While algorithmic developments enable neural networks to solve increasingly…
Transfer learning enhances the training of novel sensory and decision models by employing rich feature representations from large, pre-trained teacher models. Cognitive neuroscience shows that the human brain creates low-dimensional,…
Binary neural networks are the extreme case of network quantization, which has long been thought of as a potential edge machine learning solution. However, the significant accuracy gap to the full-precision counterparts restricts their…
Binary Neural Networks (BNNs) can drastically reduce memory size and accesses by applying bit-wise operations instead of standard arithmetic operations. Therefore it could significantly improve the efficiency and lower the energy…
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to…
Binarization is a powerful compression technique for neural networks, significantly reducing FLOPs, but often results in a significant drop in model performance. To address this issue, partial binarization techniques have been developed,…
With the remarkable progress that technology has made, the need for processing data near the sensors at the edge has increased dramatically. The electronic systems used in these applications must process data continuously, in real-time, and…
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…
Spin chains can be used to describe a wide range of platforms for quantum computation and quantum information. They enable the understanding, demonstration, and modeling of numerous useful phenomena, such as high fidelity transfer of…
Binary Neural Networks (BNNs) enable efficient deep learning by saving on storage and computational costs. However, as the size of neural networks continues to grow, meeting computational requirements remains a challenge. In this work, we…
It is widely perceived that leveraging the success of modern machine learning techniques to mobile devices and wireless networks has the potential of enabling important new services. This, however, poses significant challenges, essentially…
Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting…
Binary neural networks (BNNs) have demonstrated their ability to solve complex tasks with comparable accuracy as full-precision deep neural networks (DNNs), while also reducing computational power and storage requirements and increasing the…
The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…
Deep Convolutional Neural Networks (CNNs) have become state-of-the art for computer vision and other signal processing tasks due to their superior accuracy. In recent years, large efforts have been made to reduce the computational costs of…
Efficient inference of Deep Neural Networks (DNNs) is essential to making AI ubiquitous. Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. These techniques translate into…
Traditional neural networks assume vectorial inputs as the network is arranged as layers of single line of computing units called neurons. This special structure requires the non-vectorial inputs such as matrices to be converted into…
Deep neural networks (DNNs) and decision trees (DTs) are both state-of-the-art classifiers. DNNs perform well due to their representational learning capabilities, while DTs are computationally efficient as they perform inference along one…
In this paper, we examine a basic smart meter network topology in mininet and address the issue of congestion over a commodity network, proposing an adaptive algorithm to cope with varying grid data delivery latencies.
Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem,…