Related papers: Multiply-and-Fire (MNF): An Event-driven Sparse Ne…

To address memory and computation resource limitations for hardware-oriented acceleration of deep convolutional neural networks (CNNs), we present a computation flow, stacked filters stationary flow (SFS), and a corresponding data encoding…

Adversarial attacks have exposed serious vulnerabilities in Deep Neural Networks (DNNs) through their ability to force misclassifications through human-imperceptible perturbations to DNN inputs. We explore a new direction in the field of…

Convolutional neural networks (CNNs) are now the de facto solution for computer vision problems thanks to their impressive results and ease of learning. These networks are composed of layers of connected units called artificial neurons,…

Computer-science-oriented artificial neural networks (ANNs) have achieved tremendous success in a variety of scenarios via powerful feature extraction and high-precision data operations. It is well known, however, that ANNs usually suffer…

Facial Expression Recognition (FER) is an active research domain that has shown great progress recently, notably thanks to the use of large deep learning models. However, such approaches are particularly energy intensive, which makes their…

As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area of research in this field is sparsity - encouraging zero…

Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and…

Event-based cameras display great potential for a variety of tasks such as high-speed motion detection and navigation in low-light environments where conventional frame-based cameras suffer critically. This is attributed to their high…

Reducing energy consumption is a critical point for neural network models running on edge devices. In this regard, reducing the number of multiply-accumulate (MAC) operations of Deep Neural Networks (DNNs) running on edge hardware…

Sparse connectivity is a hallmark of the brain and a desired property of artificial neural networks. It promotes energy efficiency, simplifies training, and enhances the robustness of network function. Thus, a detailed understanding of how…

The state-of-the-art accelerators for Convolutional Neural Networks (CNNs) typically focus on accelerating only the convolutional layers, but do not prioritize the fully-connected layers much. Hence, they lack a synergistic optimization of…

Spiking Neural Networks (SNNs) have been put forward as an energy-efficient alternative to Artificial Neural Networks (ANNs) since they perform sparse Accumulate operations instead of the power-hungry Multiply-and-Accumulate operations.…

Spiking Neural Networks (SNNs) compute in an event-based matter to achieve a more efficient computation than standard Neural Networks. In SNNs, neuronal outputs (i.e. activations) are not encoded with real-valued activations but with…

Machine learning is increasingly used to improve decisions within branch-and-bound algorithms for mixed-integer programming. Many existing approaches rely on deep learning, which often requires very large training datasets and substantial…

Event camera, as an asynchronous vision sensor capturing scene dynamics, presents new opportunities for highly efficient 3D human pose tracking. Existing approaches typically adopt modern-day Artificial Neural Networks (ANNs), such as CNNs…

Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often…

Sparsity is an intrinsic property of convolutional neural network(CNN) and worth exploiting for CNN accelerators, but extra processing comes with hardware overhead, causing many architectures suffering from only minor profit. Meanwhile,…

Deploying deep learning models on mobile devices draws more and more attention recently. However, designing an efficient inference engine on devices is under the great challenges of model compatibility, device diversity, and resource…

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…

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…