Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 23 for “"Neural Network Pruning"”.
-
Neural Network Pruning for ECG Arrhythmia Classification
Convolutional Neural Networks (CNNs) are a widely accepted means of solving complex classification and detection problems in imaging and speech. However, problem complexity often leads to considerable increases in computation and parameter storage costs. Many successful attempts have been made in …
-
Fine Granularity is Critical for Intelligent Neural Network Pruning
Neural network pruning is a popular approach to reducing the computational costs of training and/or deploying a network, and aims to do so while minimizing accuracy loss. Pruning methods that remove individual weights (fine granularity) yield better ratios of accuracy to parameter count, while …
-
Deep Neural Network Pruning and Sensor Fusion in Practical 2D Detection
Convolutional Neural Networks (CNNs) have been extensively studied and applied to various computer vision problems, including object detection, semantic segmentation, and autonomous driving. Convolutional Neural Networks (CNN)s extract complex features from input images or data to represent objects …
-
Efficient Deep Neural Network Pruning: From Convolutional Networks to Large Language Models
Neural network pruning is a widely used compression technique. However, minimal performance degradation can make pruning resource-intensive, requiring substantial computational and memory overhead. It becomes particularly challenging when resources are limited. This thesis delves into the …
-
Applications of Markov Random Field Optimization and 3D Neural Network Pruning in Computer Vision
… witness the rapid development of Convolutional Neural Network (CNN) in various computer vision applications that were traditionally addressed by Markov Random Field (MRF) optimization methods. Even though CNN based methods achieve high accuracy in these tasks, a high level of fine results are …
-
PRUNING NEURAL NETWORKS USING DETERMINANTAL POINT PROCESSES
Neural network pruning aims at lowering the complexity of a query to a neural network which is already trained. In this scope, various strategies can be imagined in order to find a sub network, which performs nearly as optimally as the main one, without having to relearn a second time. In this …
-
Zonotope matching and approximation for neural networks
… linear function is pointwise equal to a ReLU neural network of depth two. These criteria are obtained by passing to the convex dual and enumerating a series of algebraic and polyhedral conditions under which pointwise equality must hold. In addition, we provide an algorithm and framework for …
-
LESS IS MORE: IMPROVING THE PERFORMANCE OF LEARNING MODELS WITH FEWER FEATURES OR FEWER PARAMETERS
… and propose three methods: feature selection, neural network pruning and time series forecasting, where the first method addresses the issue of growing number of features and the latter two methods address the issue of growing number of model parameters.
-
Efficient Sparse Neural Network Training
Developments in neural networks have led to advanced models requiring large amounts of training time and resources. To reduce the environmental impact and to decrease the training times of models, acceleration techniques have been developed. One method is neural network pruning, which removes …
-
Towards Artificially Intelligent Communications
… (interpretability & generalizability), (2) neural network pruning methods enabling edge-ready AI (interpretability & deployability), and (3) a gray-box, physics-based AI simulation tool for fiber optic networks (interpretability & generalizability). This thesis demonstrates advancements in …
-
Sparse deep neural networks for modeling physical and biological systems
Characterizing the relationship between network performance and its parameters is an active area of investigation within the fields of deep learning and complex network science. In this thesis, sparse deep neural networks (DNNs) are explored as tools for modeling physical and biological systems and …
-
Distribution approximation in deep learning
… uncertainty quantification. Another example is neural network pruning, which can be viewed as approximating the distribution of neurons at each layer using a distribution with much fewer neurons. In this dissertation, we discuss algorithms for distribution approximation under different …
-
The Hidden Structure of Deep Models: Discovering and Exploiting Sparse Subnetworks
… in sparse nonnegative matrix factorization and neural network pruning. Second, Data Adaptive Pathway Discovery (DAPD) learns sparse reinforcement-learning pathways under changing data distributions. It adapts masks during a warm-up phase and freezes them for stable optimization. Across …
-
Study on Performance of Pruned CNN-based Classification Models
Convolutional Neural Network (CNN) is a neural network developed for processing image data. CNNs have been studied extensively and have been used in numerous computer vision tasks such as image classification and segmentation, object detection and recognition, etc. [1] Although, the CNNs-based …
-
Submodular Cover and Maximization: Approximation Algorithms, Bandit Feedback, and Reinforcement Learning
… recommendation systems, data summarization, and neural network pruning. The study of submodular optimization centers on two fundamental problems: Submodular Maximization (SM) and Submodular Cover (SC). In SM, the objective is to select a subset of elements from a universe U that maximizes a …
-
Pruning resnet neural networks block by block
Neural network pruning has gained popularity for deep models with the goal of reducing storage and computational requirements, both for inference and training. Pruning weights from neural networks to make models sparse has been discussed for a long time starting with in 1990s. Structured pruning is …
-
Explicit Group Sparse Projection for Machine Learning
… errors against state-of-the-art algorithms. In neural network pruning, the sparse models produced by our method have competitive accuracy at corresponding sparsity values compared to existing methods.
-
Nonlinear Regression Based on Neural Networks: Prediction, Sufficient Dimension Reduction, and Model Compression
In the modern era, neural networks have achieved great success in various fields of applications. Since neural networks allow the modeling of nonlinear relationships, they have become popular and useful tools for tackling different problems such as prediction, classification, clustering, dimension …
-
Fair Compression of Machine Learning Vision Systems
Model pruning is a simple and effective method for compressing neural networks. By identifying and removing the least influential parameters of a model, pruning is able to transform networks into smaller, faster networks with minimal impact to overall perfor- mance. However, recent research has …
-
Achieving More with Less: Learning Generalizable Neural Networks With Less Labeled Data and Computational Overheads
… exploring different ways to learn generalizable neural networks that require less labeled data and computational resources. We demonstrate that using physics supervision in scientific problems can reduce the need for labeled data, thereby improving data efficiency without compromising model …
Page 1 of 2