Related papers: Constrained deep neural network architecture searc…
The rapid proliferation of computing domains relying on Internet of Things (IoT) devices has created a pressing need for efficient and accurate deep-learning (DL) models that can run on low-power devices. However, traditional DL models tend…
In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has…
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural…
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives…
IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persistent storage, which is orders of magnitude fewer…
Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally…
In recent years Deep Learning reached significant results in many practical problems, such as computer vision, natural language processing, speech recognition and many others. For many years the main goal of the research was to improve the…
This paper presents a hardware-efficient deep neural network (DNN), optimized through hardware-aware neural architecture search (HW-NAS); the DNN supports the classification of session-level encrypted traffic on resource-constrained…
Automatic algorithm-hardware co-design for DNN has shown great success in improving the performance of DNNs on FPGAs. However, this process remains challenging due to the intractable search space of neural network architectures and hardware…
The search space of neural architecture search (NAS) for convolutional neural network (CNN) is huge. To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only. Such…
The growing capacity of neural networks has strongly contributed to their success at complex machine learning tasks and the computational demand of such large models has, in turn, stimulated a significant improvement in the hardware…
Recent advances in deep learning motivate the use of deep neutral networks in sensing applications, but their excessive resource needs on constrained embedded devices remain an important impediment. A recently explored solution space lies…
Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Object Detection. However, many other relevant applications of…
Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes…
Artificial neural networks have gone through a recent rise in popularity, achieving state-of-the-art results in various fields, including image classification, speech recognition, and automated control. Both the performance and…
The majority of IoT devices like smartwatches, smart plugs, HVAC controllers, etc., are powered by hardware with a constrained specification (low memory, clock speed and processor) which is insufficient to accommodate and execute large,…
Early advancements in convolutional neural networks (CNNs) architectures are primarily driven by human expertise and by elaborate design processes. Recently, neural architecture search was proposed with the aim of automating the network…
Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal…
Deploying deep learning models requires taking into consideration neural network metrics such as model size, inference latency, and #FLOPs, aside from inference accuracy. This results in deep learning model designers leveraging…
Neural Architecture Search (NAS) has been a source of dramatic improvements in neural network design, with recent results meeting or exceeding the performance of hand-tuned architectures. However, our understanding of how to represent the…