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 36 for “"Architecture Search"”.

  1. 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 …

    must-thes Repository record for Computational model for neural architecture search (opens in a new tab)

  2. 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 …

    mit Repository record for Mixed-precision NN accelerator with neural-hardware architecture search (opens in a new tab)

  3. 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 …

    pretoria Repository record for Multi-objective evolutionary neural architecture search for recurrent neural networks (opens in a new tab)

  4. 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, …

    passau-thes Repository record for Structure of Artificial Neural Networks : Empirical Investigations (opens in a new tab)

  5. 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. …

    uts Repository record for Learning Neural Network Architecture from Data: NAS and Dynamic Networks (opens in a new tab)

  6. Towards practical neural network meta-modeling

    … for convolutional neural network (CNN) architecture search. We first introduce a novel approach for CNN architecture architecture using Q-learning, a popular value iteration algorithm from the reinforcement learning community for sequential decision problems. On the task of object …

    mit Repository record for Towards practical neural network meta-modeling (opens in a new tab)

  7. Automated and Handcrafted Neural Network Design for Vision Applications

    … in the first step, it applies novel neural architecture search algorithms on single image deraining and re-identification (reID), where unique deraining and reID search space are proposed, respectively. To step further, this thesis also introduces elaborately handcrafted networks, such as a …

    uts Repository record for Automated and Handcrafted Neural Network Design for Vision Applications (opens in a new tab)

  8. Taming TinyML: deep learning inference at computational extremes

    … for deep learning, is tackled by the emerging research field called *TinyML*. In this thesis, I develop model discovery and compression methodology whose common threads are automation and holistic optimisation of network architectures and their execution software, informed by the computational …

    cambridge Repository record for Taming TinyML: deep learning inference at computational extremes (opens in a new tab)

  9. 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 …

    bournemouth Repository record for Efficient Multi-Objective NeuroEvolution in Computer Vision and Applications for Threat Identification (opens in a new tab)

  10. 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 …

    uoit Repository record for Towards searching for the best student in a Knowledge Distillation framework (opens in a new tab)

  11. 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 …

    nus Repository record for TOWARDS EFFICIENT LARGE-SCALE BI-LEVEL OPTIMIZATION, ALGORITHMS AND APPLICATIONS (opens in a new tab)

  12. Technology selection and architecture optimization of in-situ resource utilization systems

    … the resources spent on exploiting individual architectures and exploring a broad selection of architectures. These include two dual-level approaches that address the discrete architecture design space differently from the continuous sizing design space and two combinatorial approaches that …

    mit Repository record for Technology selection and architecture optimization of in-situ resource utilization systems (opens in a new tab)

  13. Software and Hardware Co-design for Efficient Neural Networks

    … hardware-awareness to produce efficient network architectures for emerging types of neural networks and new learning problem setups. Hardware-aware network architecture search (NAS) is able to discover more power efficient network architectures and achieve significant computational savings on …

    cambridge Repository record for Software and Hardware Co-design for Efficient Neural Networks (opens in a new tab)

  14. Design of Deep Neural Networks Formulated as Optimisation Problems

    … involves the explicit definition of network architecture as well as the training of the network weights. Each process can be formulated into an optimisation algorithm and can be investigated with regard to optimisation performance. The training of the network weights is defined as a …

    cambridge Repository record for Design of Deep Neural Networks Formulated as Optimisation Problems (opens in a new tab)

  15. 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 …

    duke Repository record for On Impact of Network Architecture for Deep Learning (opens in a new tab)

  16. Reliable, secure and energy-efficient AI hardware

    … as explainable artificial intelligence, neural architecture search, and moving target defense to guarantee reliability, security, and energy efficiency. My Ph.D. thesis is the first effort toward developing energy, reliability, and robustness-aware AI hardware for safety-critical applications.

    missouri Repository record for Reliable, secure and energy-efficient AI hardware (opens in a new tab)

  17. Searching for Efficient Multi-Stage Vision Transformers

    … present ViT-ResNAS, an efficient multi-stage ViT architecture designed with neural architecture search (NAS). First, we propose residual spatial reduction to decrease sequence lengths for deeper layers and utilize a multi-stage architecture. When reducing lengths, we add skip connections to …

    mit Repository record for Searching for Efficient Multi-Stage Vision Transformers (opens in a new tab)

  18. Evolutionary Optimization of Neural Architectures for Remaining Useful Life Prediction

    … 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, we propose evolutionary neural architecture search (NAS) techniques that explore a search

    trento Repository record for Evolutionary Optimization of Neural Architectures for Remaining Useful Life Prediction (opens in a new tab)

  19. 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 …

    stellenbosch Repository record for Machine Learning for Physics Applications: Quantum Algorithm Design, Chaotic Dynamics, and Mass Spectrometry (opens in a new tab)

  20. Computer Vision with Machine Learning on Smartphones for Beauty Applications.

    … network execution a highly active area of research, as evidenced by Google’s TensorFlow Lite platform and Apple’s CoreML API and Neural Engine-accelerated iOS devices. The overarching goal of the projects carried out in this thesis is to adapt existing desktop computer-oriented computer …

    bournemouth Repository record for Computer Vision with Machine Learning on Smartphones for Beauty Applications. (opens in a new tab)

Page 1 of 2