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 29 for “"Neural Architecture Search"”.
-
Computational model for neural architecture search
<p>"A long-standing goal in Deep Learning (DL) research is to design efficient architectures for a given dataset that are both accurate and computationally inexpensive. At present, designing deep learning architectures for a real-world application requires both human expertise and considerable …
-
Multi-objective evolutionary neural architecture search for recurrent neural networks
Artificial neural network (ANN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of ANN architectures, and has proven to be successful in finding ANN architectures that can …
-
Structure of Artificial Neural Networks : Empirical Investigations
… intelligence. "Deep" refers to the deep architectures with operations in manifolds of which there are no immediate observations. For these deep architectures some kind of structure is pre-defined -- but what is this structure? With a formal definition for structures of neural networks, …
-
Learning Neural Network Architecture from Data: NAS and Dynamic Networks
A myriad of breakthroughs in neural network architecture has brought significant improvement on wide range of deep learning tasks. Despite the large advances brought about by network design, manually finding well-optimized network architecture is challenging given large amount of design choices. …
-
Automated and Handcrafted Neural Network Design for Vision Applications
This thesis presents effective neural network design for various vision applications from two aspects, automated neural network design and handcrafted neural network design. To be more specific, in the first step, it applies novel neural architecture search algorithms on single image deraining and …
-
Efficient Multi-Objective NeuroEvolution in Computer Vision and Applications for Threat Identification
… to classic, effort-intensive hyperparameter search. However, existing approaches typ- ically show significant downsides, like their (1) high computational cost/greediness in resources, (2) limited (or absent) scalability to custom datasets, (3) inability to provide competitive alternatives to …
-
Towards searching for the best student in a Knowledge Distillation framework
… of identifying an optimal student—balancing architecture and training hyperparameters—is often hindered by the extensive and computationally intensive search required. This thesis introduces the KD-Policy-Learning (KD-PL) framework, a novel approach designed to mitigate this challenge. KD-PL …
-
TOWARDS EFFICIENT LARGE-SCALE BI-LEVEL OPTIMIZATION, ALGORITHMS AND APPLICATIONS
… mathematical framework with a long history of research, dealing with hierarchical optimization problems where one problem is nested within the other. Recently, with the rise of machine learning, bi-level optimization has regained attention as a theoretical framework covering a wide range of …
-
Mixed-precision NN accelerator with neural-hardware architecture search
Neural architecture and hardware architecture co-design is an effective way to enable specialization and acceleration for deep neural networks (DNNs). The design space and its exploration methodology impact efficiency and productivity. However, both architecture designs are challenging. We first …
-
On Impact of Network Architecture for Deep Learning
<p>The architecture of neural networks is a crucial factor in the success of deep learning models across a range of fields, including computer vision and natural language processing (NLP). Specific architectures are tailored to address particular tasks, and the selection of architecture can …
-
Reliable, secure and energy-efficient AI hardware
… However, similar to traditional deep neural networks (DNNs), approximate deep neural networks (AxDNNs) and approximate spiking neural networks (AxSNNs) are vulnerable to many reliability threats, such as permanent and transient faults, and security threats, such as adversarial attacks. …
-
Searching for Efficient Multi-Stage Vision Transformers
… in comparable performance to convolutional neural networks (CNN), which have been studied in computer vision for years. This naturally raises the question of how the performance of ViT can be advanced with design techniques of CNN. To this end, we propose to incorporate two techniques and …
-
Evolutionary Optimization of Neural Architectures for Remaining Useful Life Prediction
… approaches, in particular employing deep neural networks (DNNs), have shown success in the RUL prediction task. However, although their architecture considerably affects performance, DNNs are usually handcrafted by human experts via a labor-intensive design process. To overcome this issue, …
-
Machine Learning for Physics Applications: Quantum Algorithm Design, Chaotic Dynamics, and Mass Spectrometry
… quantum algorithm design, where evolutionary search with a domain-specific language enables the synthesis of quantum algorithms that automatically scale to any problem size. By rediscovering known protocols such as the quantum Fourier transform, Grover’s search, and the Deutsch–Jozsa …
-
Computer Vision with Machine Learning on Smartphones for Beauty Applications.
… strongly towards deep learning techniques with neural networks, given their relative ease of application to custom tasks, as well as their greatly improved results compared to traditional computer vision techniques. Since the execution of deep learning models is often resource-heavy, this leads …
-
Efficient Deep Learning: Model Design and Algorithmic Innovation
… training, and deployment. Central to this research is the development of advanced Neural Architecture Search (NAS) frameworks. These frameworks enable the automated design of lightweight, task-specific neural networks optimized for resource-constrained scenarios, such as mobile devices and …
-
Designing Highly-Efficient Hardware Accelerators for Robust and Automatic Deep Learning Technologies
… AI technologies, such as deep convolutional neural networks (DNNs), have recently achieved amazing success in numerous applications, such as image recognition, autonomous driving, and so on. However, there are two critical issues in the conventional DNN applications. The first problem is …
-
Improving Deep Learning with Probabilistic Approaches
… that probabilistic inference over the depth of a neural network not only side-steps challenges involved with scaling inference to the large weight spaces of modern neural networks but also provides well-calibrated uncertainty estimates and robust predictions. Furthermore, we leverage the …
-
Efficient Algorithms and Systems for Tiny Deep Learning
… a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers. TinyNAS adopts a two-stage neural architecture search approach that first optimizes the search space to fit the …
-
Taming TinyML: deep learning inference at computational extremes
The advanced data modelling capabilities of neural networks allowed deep learning to become a cornerstone of many applications of artificial intelligence (AI). AI can be brought into our environments by deploying neural models to ubiquitous Internet-of-Things (IoT), wearable and embedded devices to …
Page 1 of 2