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 5 of 5 for “"Energy-Efficient Learning"”.

  1. Intelligent Anti-Jamming Based on Deep-Reinforcement Learning and Transfer Learning

    … thesis, we first develop a deep reinforcement learning (DRL) model to confront the jammer. However, training a DRL model from scratch may take a long time. We further propose a transfer learning (TL) approach to enable the DRL agent to learn fast in dynamic wireless networks to confront jamming …

    york Repository record for Intelligent Anti-Jamming Based on Deep-Reinforcement Learning and Transfer Learning (opens in a new tab)

  2. Adaptive Hierarchical Spiking Neural Networks for Event-Driven Multi-Agent Cooperation on the Edge

    … comprehensive study of multi-agent reinforcement learning using Spiking Neural Networks (SNNs) for decentralized control in edge computing environments. Chapter 1 introduces the motivation and provides a literature review, highlighting the need for biologically inspired neural models to achieve …

    carleton Repository record for Adaptive Hierarchical Spiking Neural Networks for Event-Driven Multi-Agent Cooperation on the Edge (opens in a new tab)

  3. Design Considerations for Training Memristor Crossbars Used in Spiking Neural Networks

    … have shown to be powerful for realizing energy-efficient learning machines. These architectures are recently demonstrated in reservoir computing networks, which have reduced training complexity and resource utilization. In reservoir computing, the training time is curtailed due to random …

    rit Repository record for Design Considerations for Training Memristor Crossbars Used in Spiking Neural Networks (opens in a new tab)

  4. Design of a Device-aware Memristive Neuromorphic System with Spike Timing Dependent Learning

    … networks (SNN) present a biologically plausible energy efficient learning platform by encoding data into sparse spiking events. The discovery of memristor, a nanoelectronic device, has accelerated the development of SNNs, as the inherent plasticity of the device makes it a suitable candidate to …

    utk-theses Repository record for Design of a Device-aware Memristive Neuromorphic System with Spike Timing Dependent Learning (opens in a new tab)

  5. Toward Intelligent Machines: Conscious Learning and Hardware-Accelerated AI

    … continuously to non-stationary data, or operate efficiently on energy-constrained hardware. This dissertation addresses these limitations through four coordinated contributions spanning probabilistic learning algorithms, biologically inspired temporal memory, cross-entity warning propagation via …

    usf Repository record for Toward Intelligent Machines: Conscious Learning and Hardware-Accelerated AI (opens in a new tab)