Related papers: Sense: Model Hardware Co-design for Accelerating S…

The CNNs have achieved a state-of-the-art performance in many applications. Recent studies illustrate that CNN's recognition accuracy drops drastically if images are noise corrupted. We focus on the problem of robust recognition accuracy of…

Spiking Neural Networks (SNNs) are highly efficient due to their spike-based activation, which inherently produces bit-sparse computation patterns. Existing hardware implementations of SNNs leverage this sparsity pattern to avoid wasteful…

Many FPGAs vendors have recently included embedded processors in their devices, like Xilinx with ARM-Cortex A cores, together with programmable logic cells. These devices are known as Programmable System on Chip (PSoC). Their ARM cores…

Manufacturing-viable neuromorphic chips require novel computer architectures to achieve the massively parallel and efficient information processing the brain supports so effortlessly. Emerging event-based architectures are making this dream…

Structured sparsity enables deploying large language models (LLMs) on resource-constrained systems. Approaches like dense-to-sparse fine-tuning are particularly compelling, achieving remarkable structured sparsity by reducing the model size…

We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse…

This paper presents a configurable Convolutional Neural Network Accelerator (CNNA) for a System on Chip design (SoC). The goal was to accelerate inference of different deep learning networks on an embedded SoC platform. The presented CNNA…

In recent years Deep Learning reached significant results in many practical problems, such as computer vision, natural language processing, speech recognition and many others. For many years the main goal of the research was to improve the…

Resistive Random-Access-Memory (ReRAM) crossbar is a promising technique for deep neural network (DNN) accelerators, thanks to its in-memory and in-situ analog computing abilities for Vector-Matrix Multiplication-and-Accumulations (VMMs).…

Convolutional neural networks (CNNs) are one of the most successful machine learning techniques for image, voice and video processing. CNNs require large amounts of processing capacity and memory bandwidth. Hardware accelerators have been…

Systolic array accelerators execute CNNs with energy dominated by the switching activity of multiply accumulate (MAC) units. Although prior work exploits weight dependent MAC power for compression, existing methods often use global…

The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices. This work introduces convolutional layers with pre-defined…

Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies, achieving high accuracy on computer vision workloads such as image classification and object detection. However, training…

Sparse linear algebra is crucial in many application domains, but challenging to handle efficiently in both software and hardware, with one- and two-sided operand sparsity handled with distinct approaches. In this work, we enhance an…

Existing deep convolutional neural networks (CNNs) generate massive interlayer feature data during network inference. To maintain real-time processing in embedded systems, large on-chip memory is required to buffer the interlayer feature…

Hardware accelerators for convolution neural networks (CNNs) enable real-time applications of artificial intelligence technology. However, most of the existing designs suffer from low hardware utilization or high area cost due to complex…

Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (SPM) is presented to encode the sparsity in PCNN. Leveraging…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

Deep convolutional neural networks (CNNs) obtain outstanding results in tasks that require human-level understanding of data, like image or speech recognition. However, their computational load is significant, motivating the development of…

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…