Related papers: ChamNet: Towards Efficient Network Design through …

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be…

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…

As deep neural network (NN) methods have matured, there has been increasing interest in deploying NN solutions to "edge computing" platforms such as mobile phones or embedded controllers. These platforms are often resource-constrained,…

The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain,…

Automatic search of neural network architectures is a standing research topic. In addition to the fact that it presents a faster alternative to hand-designed architectures, it can improve their efficiency and for instance generate…

Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic…

Differentiable neural architecture search methods became popular in recent years, mainly due to their low search costs and flexibility in designing the search space. However, these methods suffer the difficulty in optimizing network, so…

Bayesian method is capable of capturing real world uncertainties/incompleteness and properly addressing the over-fitting issue faced by deep neural networks. In recent years, Bayesian Neural Networks (BNNs) have drawn tremendous attentions…

Recent progress in computer vision-oriented neural network designs is mostly driven by capturing high-order neural interactions among inputs and features. And there emerged a variety of approaches to accomplish this, such as Transformers…

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…

Deep convolutional neural networks (CNNs) have been widely used in surface defect detection. However, no CNN architecture is suitable for all detection tasks and designing effective task-specific requires considerable effort. The neural…

Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An…

We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost. For instance, our approach is able to solve the following tasks: learn a neural network able to predict…

Computing-in-memory (CIM) is an emerging computing paradigm, offering noteworthy potential for accelerating neural networks with high parallelism, low latency, and energy efficiency compared to conventional von Neumann architectures.…

Bayesian Neural Networks (BNNs) provide principled estimates of model and data uncertainty by encoding parameters as distributions. This makes them key enablers for reliable AI that can be deployed on safety critical edge systems. These…

Convolutional neural networks (CNNs) demand huge DRAM bandwidth for computational imaging tasks, and block-based processing has recently been applied to greatly reduce the bandwidth. However, the induced additional computation for feature…

In recent years, transformer models have revolutionized Natural Language Processing (NLP) and shown promising performance on Computer Vision (CV) tasks. Despite their effectiveness, transformers' attention operations are hard to accelerate…

While the transformer architecture has achieved state-of-the-art performance on natural language processing tasks, these models impose substantial memory and computational overhead. Recent research has identified significant architectural…

Neural networks have recently had a lot of success for many tasks. However, neural network architectures that perform well are still typically designed manually by experts in a cumbersome trial-and-error process. We propose a new method to…

The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular…