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 10 of 10 for “"Efficient AI"”.

  1. Efficient AI hardware acceleration

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-04-12 without embargo terms

    uiuc Repository record for Efficient AI hardware acceleration (opens in a new tab)

  2. Reliable, secure and energy-efficient AI hardware

    The embedded AI hardware chips are being widely used in consumer devices and enterprise markets, such as high-end smartphones, tablets, smart speakers, wearables, autonomous vehicles, cameras, sensors, and other IoT (internet of things) devices. According to a recent report, the embedded AI

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

  3. Towards Efficient AI for Science in Scalable and High Performance Distributed System

    Artificial intelligence (AI) has seen rapid development over the last few decades, significantly impacting various domains such as computer vision and natural language processing. In recent years, machine learning methods have been increasingly applied to the scientific discovery process, …

    unr Repository record for Towards Efficient AI for Science in Scalable and High Performance Distributed System (opens in a new tab)

  4. Robust and Efficient AI-models for Medical Image Reconstruction, Segmentation, and Multimodal Knowledge Distillation

    Artificial intelligence (AI) is transforming the healthcare landscape, offering the promise of earlier diagnoses, more personalized treatments, and improved patient outcomes. However, despite its tremendous potential, deploying AI in real-world clinical settings remains fraught with challenges. …

    unr Repository record for Robust and Efficient AI-models for Medical Image Reconstruction, Segmentation, and Multimodal Knowledge Distillation (opens in a new tab)

  5. Automated Finetuning via Sparse Autoencoders

    … approach achieves competitive performance against larger monolithic models in specialized domains, while utilizing fewer parameters, training examples, and computational resources. The framework’s modularity enables independent optimization of components from sparse autoencoders to MoIE …

    mit Repository record for Automated Finetuning via Sparse Autoencoders (opens in a new tab)

  6. Mechanistic Interpretability for Progress Towards Quantitative AI Safety

    In this thesis, we conduct a detailed investigation into the dynamics of neural networks, focusing on two key areas: inference stages in large language models (LLMs) and novel program synthesis methods using mechanistic interpretability. We explore the robustness of LLMs through layer-level …

    mit Repository record for Mechanistic Interpretability for Progress Towards Quantitative AI Safety (opens in a new tab)

  7. Energy-Efficient Neural Network Hardware Design and Circuit Techniques to Enhance Hardware Security

    Artificial intelligence (AI) algorithms and hardware are being developed at a rapid pace for emerging applications such as self-driving cars, speech/image/video recognition, deep learning, etc. Today’s AI tasks are mostly performed at remote datacenters, while in the future, more AI workloads are …

    umn Repository record for Energy-Efficient Neural Network Hardware Design and Circuit Techniques to Enhance Hardware Security (opens in a new tab)

  8. MODEL ADAPTATION FOR EDGE AI

    … hardware, advocating for flexible and efficient models. Firstly, we tackle the challenge of on-device adaptation for user-specific models. Given the limited on-chip memory in edge devices, data movement becomes a significant bottleneck, leading to increased energy consumption. We …

    nus Repository record for MODEL ADAPTATION FOR EDGE AI (opens in a new tab)

  9. Efficient Deep Learning: Model Design and Algorithmic Innovation

    The rapid evolution of Artificial Intelligence (AI) and Deep Learning (DL) has revolutionized numerous domains, from computer vision to natural language processing and intelligent recommendation systems. However, this progress has been accompanied by escalating computational demands that challenge …

    unsw Repository record for Efficient Deep Learning: Model Design and Algorithmic Innovation (opens in a new tab)

  10. Efficient Continual Learning and On-Device Training for Mobile and IoT Devices

    … to changing real-world conditions, despite constraints such as limited labelled data, memory, and computational power. However, achieving continual learning (CL) and on-device training on resource-constrained edge devices poses significant challenges, both in terms of resource limitations and the …

    cambridge Repository record for Efficient Continual Learning and On-Device Training for Mobile and IoT Devices (opens in a new tab)