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 160 for “"model compression"”.
-
Speech recognition model compression
Speech recognition models are widely deployed in mobile and embedded devices. However, the base architecture with which these models are developed is usually made of neural networks with bigger size and millions of model parameters. In this report, we investigate three compression schemes for these …
-
Data-Constrained Model Compression
… in compressing compute-heavy machine learning models to enable them to execute in real-time on edge devices. Typically, model compression techniques require retraining a model on the original dataset of interest. This is problematic if the original dataset is unavailable due to privacy or legal …
-
Model Compression via Generalized Kronecker Product Decomposition
… bandwidth capabilities. The design of efficient models as well as automated compression methodologies such as quantization, pruning, knowledge distillation and tensor decomposition have been proposed to allow models to operate in such resource-constrained environments. In particular, tensor …
-
Efficient signal acquisition and deep learning model compression
The ubiquitous use of deep learning models for signal processing has led to an increasing computational and storage cost, especially in edge applications. Although deep learning has delivered improved accuracy for a given task, they have also increased the need for bringing in efficiency during …
-
Neural Networks as Databases - From Data to Model Compression
… this would mean moving from the paradigm of data compression towards model compression. This thesis introduces and investigates a variety of methods in the realm of model compression, with the eventual goal of replacing data compression itself. To explore this, we start with the most information …
-
Hardware-Friendly Model Compression techniques for Deep Learning Accelerators
… through developing hardware-aware \gls{dnn} compression methods. The rising popularity of intelligent mobile devices and the computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. In particular, we proposed four compression techniques for …
-
Multimodal Data Fusion and Model Compression Methods for Computer Vision
… performance. This approach not only enhances model efficiency but also facilitates real-time inference suitable for edge deployment. Additionally, we extend the TT compression technique to convolutional auto-encoders (CAEs), creating the CAE-TT, which adjusts the number of parameters without …
-
Lightweight ML-Based Drone Intrusion Detection System through Model Compression
… balance between security, efficiency, and model accuracy without significantly compromising detection performance. Hence, two complementary main contributions are proposed: First, a lightweight ML-based NIDS optimized for individual drones, utilizing a quantized deep neural network (DNN) …
-
Flexi-Compression: A Flexible Model Compression Method for Autonomous Driving
… power. In this paper, we propose an innovative model compression approach to compress convolutional neural networks in autonomous driving algorithms, which we call Flexi-Compression. Flexi-Compression first modifies the model structure by replacing the traditional convolutional layers with our …
-
Kernel-Controlled DQN Based CNN Pruning for Model Compression and Acceleration
… the size of convolutional neural networks (CNN) models is another principal factor for facilitating the deployment of models on memory, power and budget constrained devices. However, conventional model compression techniques require human experts to setup parameters to explore the design space …
-
Pruning visual transformers to increase model compression and decrease inference time
… reductions in inference time without sacrificing model accuracy. Different pruning rates were evaluated, demonstrating a trade-off between training speed and model compression. Slower pruning rates allowed for better convergence to higher accuracy levels and more efficient model recovery. …
-
Co-Designing Model Compression Algorithms and Hardware Accelerators for Efficient Deep Learning
… factors such as the growing complexity of DNN models, the diminished benefits of technology scaling, and the proliferation of resource-constrained edge devices are driving a demand for higher DNN performance and energy efficiency. Consequently, neural network training and inference have begun …
-
Nonlinear Regression Based on Neural Networks: Prediction, Sufficient Dimension Reduction, and Model Compression
… 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 reduction, visualization, computer vision, and many others. This thesis focuses …
-
Topology-aware efficient and transferable model compression using graph representation and reinforcement learning
… across many domains. However, deploying these models on devices with limited computational and storage capabilities, like mobile devices, poses significant challenges. Model compression, aiming to make these large models more efficient without significant performance loss, is an active research …
-
Early-bird training and hierarchical hardware-aware model compression towards green and ubiquitous artificial intelligence
… remain between the powerful yet large-scale AI models and the computational constraints of both edge and cloud platforms, including (1) the efficiency gap, which hinders the acceleration of AI training and the ability to iterate quickly; (2) the scalability gap, which challenges efficient …
-
Optimization of battery AI models for edge deployment: A systematic study of model compression techniques and hardware-aware efficiency
… systems (BMS) increasingly employ data-driven models to estimate battery state of health (SoH), but deploying such models on automotive microcontrollers remains challenging because of limited memory and computational resources. This thesis evaluates a hardware-aware workflow for transferring, …
-
Leveraging Model Flexibility and Deep Structure: Non-Parametric and Deep Models for Computer Vision Processes with Applications to Deep Model Compression
… object localization, object tracking and model compression. With respect to object localization, I introduce a method to perform active localization by modeling spatial and other relationships between objects in a coherent "visual situation" using a set of probability distributions. I …
Page 1 of 8