Related papers: Workload-Aware Hardware Accelerator Mining for Dis…
Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing…
The automation of feature extraction of machine learning has been successfully realized by the explosive development of deep learning. However, the structures and hyperparameters of deep neural network architectures also make huge…
Deep learning has been postulated as a solution for numerous problems in different branches of science. Given the resource-intensive nature of these models, they often need to be executed on specialized hardware such graphical processing…
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the policy vectors defined…
Spiking Neural Networks (SNNs) have emerged as a promising approach to improve the energy efficiency of machine learning models, as they naturally implement event-driven computations while avoiding expensive multiplication operations. In…
Training deep neural networks (DNNs) is a computationally expensive job, which can take weeks or months even with high performance GPUs. As a remedy for this challenge, community has started exploring the use of more efficient data…
Configurable synaptic delays are a basic feature in many neuromorphic neural network hardware accelerators. However, they have been rarely used in model implementations, despite their promising impact on performance and efficiency in tasks…
It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…
As machine learning (ML) algorithms get deployed in an ever-increasing number of applications, these algorithms need to achieve better trade-offs between high accuracy, high throughput and low latency. This paper introduces NASH, a novel…
Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNNs have been proposed, selecting and designing the…
While maximizing deep neural networks' (DNNs') acceleration efficiency requires a joint search/design of three different yet highly coupled aspects, including the networks, bitwidths, and accelerators, the challenges associated with such a…
This paper examines the design space trade-offs of DNNs accelerators aiming to achieve competitive performance and efficiency metrics for all four combinations of dense or sparse activation/weight tensors. To do so, we systematically…
Efficiently scaling deep neural networks across GPU clusters requires navigating complex trade-offs between computational throughput, memory utilization, and synchronization overhead. This paper presents a unified empirical evaluation of…
Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…
Driver intention recognition studies increasingly rely on deep neural networks. Deep neural networks have achieved top performance for many different tasks, but it is not a common practice to explicitly analyse the complexity and…
Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…
This paper studies a deep learning (DL) framework to solve distributed non-convex constrained optimizations in wireless networks where multiple computing nodes, interconnected via backhaul links, desire to determine an efficient assignment…
With rapidly increasing distributed deep learning workloads in large-scale data centers, efficient distributed deep learning framework strategies for resource allocation and workload scheduling have become the key to high-performance deep…
This paper describes various design considerations for deep neural networks that enable them to operate efficiently and accurately on processing-in-memory accelerators. We highlight important properties of these accelerators and the…
Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based…