Related papers: Tiny but Accurate: A Pruned, Quantized and Optimiz…

Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of…

Non-volatile memory (NVM) crossbars have been identified as a promising technology, for accelerating important machine learning operations, with matrix-vector multiplication being a key example. Binary neural networks (BNNs) are especially…

The deployment of deep neural networks (DNNs) on compute-in-memory (CiM) accelerators offers significant energy savings and speed-up by reducing data movement during inference. However, the reliability of CiM-based systems is challenged by…

Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time. Therefore, reducing the energy consumption has…

As neural networks gain widespread adoption in embedded devices, there is a need for model compression techniques to facilitate deployment in resource-constrained environments. Quantization is one of the go-to methods yielding…

This work is focused on the pruning of some convolutional neural networks (CNNs) and improving theirs efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn) library is the…

Deep neural networks (DNNs) are usually over-parameterized to increase the likelihood of getting adequate initial weights by random initialization. Consequently, trained DNNs have many redundancies which can be pruned from the model to…

Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e.,…

The need for deep neural network (DNN) models with higher performance and better functionality leads to the proliferation of very large models. Model training, however, requires intensive computation time and energy. Memristor-based…

Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular…

Recent years have seen deep neural networks (DNNs) becoming wider and deeper to achieve better performance in many applications of AI. Such DNNs however require huge amounts of memory to store weights and intermediate results (e.g.,…

The deployment of artificial neural networks-based optical channel equalizers on edge-computing devices is critically important for the next generation of optical communication systems. However, this is still a highly challenging problem,…

In recent years, large pre-trained Transformer networks have demonstrated dramatic improvements in many natural language understanding tasks. However, the huge size of these models brings significant challenges to their fine-tuning and…

The high computational costs associated with large deep learning models significantly hinder their practical deployment. Model pruning has been widely explored in deep learning literature to reduce their computational burden, but its…

During the deployment of deep neural networks (DNNs) on edge devices, many research efforts are devoted to the limited hardware resource. However, little attention is paid to the influence of dynamic power management. As edge devices…

Feature embeddings are one of the most essential steps when training deep learning based Click-Through Rate prediction models, which map high-dimensional sparse features to dense embedding vectors. Classic human-crafted embedding size…

Pruning is critical for scaling large language models (LLMs). Global pruning achieves strong performance but requires $\mathcal{O}(N)$ memory, which is infeasible for billion-parameter models. Local pruning reduces GPU memory usage to that…

In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be…

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on either…

Unsupervised neural nets such as Restricted Boltzmann Machines(RBMs) and Deep Belif Networks(DBNs), are powerful in automatic feature extraction,unsupervised weight initialization and density estimation. In this paper,we demonstrate that…