相关论文: MAPLE-X: Latency Prediction with Explicit Micropro…

The predictive power of Convolutional Neural Networks (CNNs) has been an integral factor for emerging latency-sensitive applications, such as autonomous drones and vehicles. Such systems employ multiple CNNs, each one trained for a…

Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation…

Neural architecture search (NAS) typically consists of three main steps: training a super-network, training and evaluating sampled deep neural networks (DNNs), and training the discovered DNN. Most of the existing efforts speed up some…

Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing when enough confidence in classification is achieved. This…

Deep neural networks have proven to be particularly effective in visual and audio recognition tasks. Existing models tend to be computationally expensive and memory intensive, however, and so methods for hardware-oriented approximation have…

We propose the Distance-informed Neural Process (DNP), a novel variant of Neural Processes that improves uncertainty estimation by combining global and distance-aware local latent structures. Standard Neural Processes (NPs) often rely on a…

Automated feature extraction capability and significant performance of Deep Neural Networks (DNN) make them suitable for Internet of Things (IoT) applications. However, deploying DNN on edge devices becomes prohibitive due to the colossal…

Deep neural networks (DNNs) have been increasingly deployed on and integrated with edge devices, such as mobile phones, drones, robots and wearables. To run DNN inference directly on edge devices (a.k.a. edge inference) with a satisfactory…

To cope with the ever-increasing computational demand of the DNN execution, recent neural architecture search (NAS) algorithms consider hardware cost metrics into account, such as GPU latency. To further pursue a fast, efficient execution,…

Almost in every heavily computation-dependent application, from 6G communication systems to autonomous driving platforms, a large portion of computing should be near to the client side. Edge computing (AI at Edge) in mobile devices is one…

Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performance evaluation. Most existing studies that achieve faster evaluation are mostly tied to cell-based…

In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture…

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of…

Designing domain specific neural networks is a time-consuming, error-prone, and expensive task. Neural Architecture Search (NAS) exists to simplify domain-specific model development but there is a gap in the literature for time series…

This study introduces the Perception Latency Mitigation Network (PLM-Net), a modular deep learning framework designed to mitigate perception latency in vision-based imitation-learning lane-keeping systems. Perception latency, defined as the…

Applying deep neural networks (DNNs) in mobile and safety-critical systems, such as autonomous vehicles, demands a reliable and efficient execution on hardware. Optimized dedicated hardware accelerators are being developed to achieve this.…

This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer, and model) to guide selective integration of heterogeneous…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

With new accelerator hardware for DNN, the computing power for AI applications has increased rapidly. However, as DNN algorithms become more complex and optimized for specific applications, latency requirements remain challenging, and it is…

Large Deep Neural Networks (DNNs) are the backbone of today's artificial intelligence due to their ability to make accurate predictions when being trained on huge datasets. With advancing technologies, such as the Internet of Things,…