Related papers: Node pruning reveals compact and optimal substruct…

Top-down induction of decision trees has been observed to suffer from the inadequate functioning of the pruning phase. In particular, it is known that the size of the resulting tree grows linearly with the sample size, even though the…

Pruning enables appealing reductions in network memory footprint and time complexity. Conventional post-training pruning techniques lean towards efficient inference while overlooking the heavy computation for training. Recent exploration of…

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…

We propose a simultaneous learning and pruning algorithm capable of identifying and eliminating irrelevant structures in a neural network during the early stages of training. Thus, the computational cost of subsequent training iterations,…

Convolutional Neural Networks (CNN) are widely used in many computer vision tasks. Yet, their increasing size and complexity pose significant challenges for efficient deployment on resource-constrained platforms. Hence, network pruning has…

The resilience of a complex interconnected system concerns the size of the macroscopic functioning node clusters after external perturbations based on a random or designed scheme. For a representation of the interconnected systems with…

Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challenges: (1) the…

Convolutional neural networks (CNNs) suffer from rapidly increasing storage and computational costs as their depth grows, which severely hinders their deployment on resource-constrained edge devices. Pruning is a practical approach for…

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks…

Contemporary state-of-the-art neural networks have increasingly large numbers of parameters, which prevents their deployment on devices with limited computational power. Pruning is one technique to remove unnecessary weights and reduce…

Exploring statistics of locally connected subgraph patterns (also known as network motifs) has helped researchers better understand the structure and function of biological and online social networks (OSNs). Nowadays the massive size of…

Neural networks achieve state-of-the-art performance in image classification, speech recognition, scientific analysis and many more application areas. Due to the high computational complexity and memory footprint of neural networks, various…

Channel pruning is a powerful technique to reduce the computational overhead of deep neural networks, enabling efficient deployment on resource-constrained devices. However, existing pruning methods often rely on local heuristics or…

Efficient data selection is crucial for enhancing the training efficiency of deep neural networks and minimizing annotation requirements. Traditional methods often face high computational costs, limiting their scalability and practical use.…

Network pruning, which removes less important parameters or architectures, is often expected to improve efficiency while preserving performance. However, this expectation does not consistently hold across language tasks: pruned models can…

Modern deep neural networks require a significant amount of computing time and power to train and deploy, which limits their usage on edge devices. Inspired by the iterative weight pruning in the Lottery Ticket Hypothesis, we propose…

With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these models on edge devices. In this paper, we provide a…

Current methods for estimating the required neural-network size for a given problem class have focused on methods that can be computationally intensive, such as neural-architecture search and pruning. In contrast, methods that add capacity…

A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to…

Machine learning models have achieved human-level performance on various tasks. This success comes at a high cost of computation and storage overhead, which makes machine learning algorithms difficult to deploy on edge devices. Typically,…