Related papers: ATHEENA: A Toolflow for Hardware Early-Exit Networ…

Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enough. Most methods rely on confidence thresholds for exiting, and consequently, improving…

Hardware-based acceleration is an extensive attempt to facilitate many computationally-intensive mathematics operations. This paper proposes an FPGA-based architecture to accelerate the convolution operation - a complex and expensive…

Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing. As we aim to execute increasingly complex tasks with constrained computational resources, much of…

While the Internet of Things (IoT) technology is booming and offers huge opportunities for information exchange, it also faces unprecedented security challenges. As an important complement to the physical layer security technologies for…

This paper presents our preliminary results with ABEONA, an edge-to-cloud architecture that allows migrating tasks from low-energy, resource-constrained devices on the edge up to the cloud. Our preliminary results on artificial and real…

Field-Programmable Gate Arrays (FPGAs) have become essential in cloud computing due to their reconfigurability, energy efficiency, and ability to accelerate domain-specific workloads. As FPGA adoption grows, research into task scheduling…

The exponential growth of multivariate time series data from sensor networks in domains like industrial monitoring and smart cities requires efficient and accurate forecasting models. Current deep learning methods often fail to adequately…

In this work, we present BasisNet which combines recent advancements in efficient neural network architectures, conditional computation, and early termination in a simple new form. Our approach incorporates a lightweight model to preview…

Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neural network (DNN) model but processes only a subset…

Anomaly detection is widely used in a broad range of domains from cybersecurity to manufacturing, finance, and so on. Deep learning based anomaly detection has recently drawn much attention because of its superior capability of recognizing…

As AI systems grow increasingly specialized and complex, managing hardware heterogeneity becomes a pressing challenge. How can we efficiently coordinate and synchronize heterogeneous hardware resources to achieve high utilization? How can…

Dynamic GNN inference has exhibited effectiveness in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC) due to strong capability to model complex particle interactions in collision events. Future HEP…

Heterogeneous Graph Neural Networks (HGNNs) have recently demonstrated great power in handling heterogeneous graph data, rendering them widely applied in many critical real-world domains. Most HGNN models leverage attention mechanisms to…

The tools employed in the DevOps Toolchain generates a large quantity of data that is typically ignored or inspected only in particular occasions, at most. However, the analysis of such data could enable the extraction of useful information…

Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural…

While deep neural networks have achieved state-of-the-art performance across a large number of complex tasks, it remains a big challenge to deploy such networks for practical, on-device edge scenarios such as on mobile devices, consumer…

Machine learning models can solve complex tasks but often require significant computational resources during inference. This has led to the development of various post-training computation reduction methods that tackle this issue in…

We introduce latency-aware network acceleration (LANA) - an approach that builds on neural architecture search techniques and teacher-student distillation to accelerate neural networks. LANA consists of two phases: in the first phase, it…

The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions that enables…

Research has shown that deep neural networks contain significant redundancy, and that high classification accuracies can be achieved even when weights and activations are quantised down to binary values. Network binarisation on FPGAs…