Related papers: SparOA: Sparse and Operator-aware Hybrid Schedulin…

Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep…

Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model…

Task scheduling is a critical research challenge in cloud computing, a transformative technology widely adopted across industries. Although numerous scheduling solutions exist, they predominantly optimize singular or limited metrics such as…

This paper presents a unified framework for codifying and automating optimization strategies to efficiently deploy deep neural networks (DNNs) on resource-constrained hardware, such as FPGAs, while maintaining high performance, accuracy,…

Advances in deep neural networks (DNNs) have significantly contributed to the development of real-time video processing applications. Efficient scheduling of DNN workloads in cloud-hosted inference systems is crucial to minimizing serving…

Structured pruning is one of the most popular approaches to effectively compress the heavy deep neural networks (DNNs) into compact sub-networks while retaining performance. The existing methods suffer from multi-stage procedures along with…

Deep Neural Network (DNN) applications with edge computing presents a trade-off between responsiveness and computational resources. On one hand, edge computing can provide high responsiveness deploying computational resources close to end…

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…

Computing sparse redundant representations is an important problem both in applied mathematics and neuroscience. In many applications, this problem must be solved in an energy efficient way. Here, we propose a hybrid distributed algorithm…

Distributed systems can be found in various applications, e.g., in robotics or autonomous driving, to achieve higher flexibility and robustness. Thereby, data flow centric applications such as Deep Neural Network (DNN) inference benefit…

Distributed DNN inference is becoming increasingly important as the demand for intelligent services at the network edge grows. By leveraging the power of distributed computing, edge devices can perform complicated and resource-hungry…

Existing deep neural networks (DNNs) that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on either activation or weight conditioned convolution operations. However, such conditional…

Splitting the inference model between device, edge server, and cloud can improve the performance of EI greatly. Additionally, the non-orthogonal multiple access (NOMA), which is the key supporting technologies of B5G/6G, can achieve massive…

Real-time Deep Neural Network (DNN) inference with low-latency requirement has become increasingly important for numerous applications in both cloud computing (e.g., Apple's Siri) and edge computing (e.g., Google/Waymo's driverless car).…

We introduce a mapping framework for deep learning inference that takes advantage of predictable neural network behavior to plan both computation and communication ahead of time. The framework generates a unified stream of instructions and…

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets.…

Spiking Neural Networks (SNNs) are inspired by the sparse and event-driven nature of biological neural processing, and offer the potential for ultra-low-power artificial intelligence. However, realizing their efficiency benefits requires…

The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches to developing new solutions for analyzing graphs and sparse data. Sparse AI analytics present unique scalability difficulties. The proposed Sparse Deep Neural Network…

Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…

The research interest in specialized hardware accelerators for deep neural networks (DNN) spikes recently owing to their superior performance and efficiency. However, today's DNN accelerators primarily focus on accelerating specific…