Related papers: PLUM: Improving Inference Efficiency By Leveraging…

Binary neural networks (BNNs) that use 1-bit weights and activations have garnered interest as extreme quantization provides low power dissipation. By implementing BNNs as computing-in-memory (CIM), which computes multiplication and…

Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation results in long inference time. Model sparsification can reduce…

With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully…

In edge intelligence systems, deep neural network (DNN) partitioning and data offloading can provide real-time task inference for resource-constrained mobile devices. However, the inference time of DNNs is typically uncertain and cannot be…

Binarized Neural Network (BNN) removes bitwidth redundancy in classical CNN by using a single bit (-1/+1) for network parameters and intermediate representations, which has greatly reduced the off-chip data transfer and storage overhead.…

Binarization is a powerful compression technique for neural networks, significantly reducing FLOPs, but often results in a significant drop in model performance. To address this issue, partial binarization techniques have been developed,…

Parallel training of neural networks at scale is challenging due to significant overheads arising from communication. Recently, deep learning researchers have developed a variety of pruning algorithms that are capable of pruning (i.e.…

We investigate pruning and quantization for deep neural networks. Our goal is to achieve extremely high sparsity for quantized networks to enable implementation on low cost and low power accelerator hardware. In a practical scenario, there…

To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The former leverages the…

From the moment Neural Networks dominated the scene for image processing, the computational complexity needed to solve the targeted tasks skyrocketed: against such an unsustainable trend, many strategies have been developed, ambitiously…

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

The biggest challenge for the deployment of Deep Neural Networks (DNNs) close to the generated data on edge devices is their size, i.e., memory footprint and computational complexity. Both are significantly reduced with quantization. With…

Recurrent neural networks (RNNs) have shown state of the art results for speech recognition, natural language processing, image captioning and video summarizing applications. Many of these applications run on low-power platforms, so their…

Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…

The success of deep neural networks (DNNs) is heavily dependent on computational resources. While DNNs are often employed on cloud servers, there is a growing need to operate DNNs on edge devices. Edge devices are typically limited in their…

Artificial neural networks open up unprecedented machine learning capabilities at the cost of ever growing computational requirements. Sparsifying the parameters, often achieved through weight pruning, has been identified as a powerful…

Deep learning as a means to inferencing has proliferated thanks to its versatility and ability to approach or exceed human-level accuracy. These computational models have seemingly insatiable appetites for computational resources not only…

DNNs deployed on analog processing in memory (PIM) architectures are subject to fabrication-time variability. We developed a new joint variability- and quantization-aware DNN training algorithm for highly quantized analog PIM-based models…

Neural network potentials (NNPs) are crucial for accelerating computational materials science by surrogating density functional theory (DFT) calculations. Improving their accuracy is possible through pre-training and fine-tuning, where an…