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 19 of 19 for “"on-chip learning"”.

  1. An on-chip learning neural network

    In this thesis, an on-chip learning neural network has been designed that uses multiplying digital-to-analog-converters (MDAC) in the synapse. The chip will take advantage of digital processing to learn and store weights, but will retain the parallel asynchronous behavior of analog systems, since …

    ttu Repository record for An on-chip learning neural network (opens in a new tab)

  2. VLSI implementation of a digital neural network with on-chip learning

    This thesis explores the VLSI implementation of a neural network with on-chip learning capabilities. This digital ASIC is intended to be used as the basis for a high-speed neural accelerator board. A unique digital neural network architecture is presented and analyzed. A novel VLSI design style is …

    manitoba Repository record for VLSI implementation of a digital neural network with on-chip learning (opens in a new tab)

  3. Processing in memory architecture for neural networks and on-chip learning acceleration

    … Two primary approaches to meet this demand are on-server learning and on-chip learning. On-server learning offers high-precision computing but consumes energy in server communication and raises privacy concerns. On the other hand, on-chip learning quickly adapts to dynamic environments and …

    gatech Repository record for Processing in memory architecture for neural networks and on-chip learning acceleration (opens in a new tab)

  4. TOWARD A RUNTIME PROGRAMMABLE SPIKING NEURAL NETWORK HARDWARE ACCELERATOR WITH ON-CHIP LEARNING

    … Neural Networks (SNNs), energy-efficient machine learning algorithms inspired by the activities of the biological brain. Due to their event-driven nature, SNNs are expected to consume less energy than Artificial Neural Networks (ANNs). However, implementing complex SNNs that achieve satisfactory …

    nus Repository record for TOWARD A RUNTIME PROGRAMMABLE SPIKING NEURAL NETWORK HARDWARE ACCELERATOR WITH ON-CHIP LEARNING (opens in a new tab) Download file for TOWARD A RUNTIME PROGRAMMABLE SPIKING NEURAL NETWORK HARDWARE ACCELERATOR WITH ON-CHIP LEARNING (opens in a new tab)

  5. A Burst-Dependent Algorithm for Neuromorphic On-Chip Learning of Spiking Neural Networks

    … for efficient neural network computing. For on-chip learning with spiking neural networks, neuromorphic hardware requires a local learning algorithm that is able to solve complex tasks. Approaches based on burst-dependent plasticity have been proposed to address this requirement, but their …

    ottawa-retro Repository record for A Burst-Dependent Algorithm for Neuromorphic On-Chip Learning of Spiking Neural Networks (opens in a new tab)

  6. Programmable Analog Techniques For Precision Analog Circuits, Low-Power Signal Processing and On-Chip Learning

    … transistors have been developed to design precision analog circuits, low-power signal processing primitives and adaptive systems that learn on-chip. Traditional analog implementations lack programmability with the result that issues such as mismatch are corrected at the expense of area. Techniques …

    gatech Repository record for Programmable Analog Techniques For Precision Analog Circuits, Low-Power Signal Processing and On-Chip Learning (opens in a new tab)

  7. Analog implementation of a current-mode Rectified Linear Unit (ReLU) for artificial neural networks

    … that can be employed in analog implementations of Artificial Neural Networks (ANNs) with on-chip learning capability. A circuit for a Rectified Linear Unit (ReLU) is proposed. The design employs current-mode inputs that are combined and applied to a tightly coupled active feedback loop that …

    texas Repository record for Analog implementation of a current-mode Rectified Linear Unit (ReLU) for artificial neural networks (opens in a new tab)

  8. Adapting Biological Mechanisms into Machine Learning Structures and Gradient Propagation

    As neuromorphic computing gains traction, researchers look for learning schemes that are more suitable for brain-like structures. Although many algorithms have been discovered, such as surrogate gradient or Spike Timing Dependent Plasticity, those algorithms are either unsuitable for on-chip …

    byu Repository record for Adapting Biological Mechanisms into Machine Learning Structures and Gradient Propagation (opens in a new tab) Download PDF for Adapting Biological Mechanisms into Machine Learning Structures and Gradient Propagation (opens in a new tab)

  9. Efficient Neuromorphic Computing Enabled by Spin-Transfer Torque: Devices, Circuits and Systems

    … expend orders of magnitude more computational resources to perform various cognitive and perception related tasks that humans routinely perform everyday. This has recently resulted in a seismic shift in the field of computation where research efforts are being directed to develop a …

    purdue-thes Repository record for Efficient Neuromorphic Computing Enabled by Spin-Transfer Torque: Devices, Circuits and Systems (opens in a new tab)

  10. Mixed-Signal Neuromorphic Circuits and Systems for Extreme-Edge Computing

    … architectures present a promising solution for integrating Internet of Things (IoT) sensors with intelligent local processing in edge computing applications. In particular, mixed-signal neuromorphic designs inherently meet key requirements of edge computing: power efficiency, compactness, …

    zurich

  11. Energy Efficient and Error Resilient Neuromorphic Computing in VLSI

    Realization of the conventional Von Neumann architecture faces increasing challenges due to growing process variations, device reliability and power consumption. As an appealing architectural solution, brain-inspired neuromorphic computing has drawn a great deal of research interest due to its …

    tamu Repository record for Energy Efficient and Error Resilient Neuromorphic Computing in VLSI (opens in a new tab)

  12. CMOS and Emerging Device Circuits for Biologically-Plausible Learning

    … emerging devices for speedy and efficient execution of machine learning models. In particular, edge computing, IoT, and mobile computing, where computing resources are limited, power budgets are low, and data is captured locally, are attractive application domains for mixed-signal and analog …

    duke Repository record for CMOS and Emerging Device Circuits for Biologically-Plausible Learning (opens in a new tab)

  13. Cross-layer methods for energy-efficient inference using in-memory architectures

    … need to acquire and process data to derive actions and interpretations in order to automate/monitor many tasks without human intervention. Such tasks require the implementation of complex machine learning algorithms on these devices. Deep neural networks (DNNs) have evolved into the …

    uiuc Repository record for Cross-layer methods for energy-efficient inference using in-memory architectures (opens in a new tab)

  14. Architectures and Training Algorithms of Deep Spiking Neural Networks

    … brain-inspired computing paradigm, is positioned to enable spatio-temporal information processing and ultra-low power event-driven neuromorphic hardware. The existing SNN architectures and their corresponding training algorithms suffer from the major limitations in terms of learning …

    tamu Repository record for Architectures and Training Algorithms of Deep Spiking Neural Networks (opens in a new tab)

  15. Bio-inspired learning and hardware acceleration with emerging memories

    Machine Learning has permeated many aspects of engineering, ranging from the Internet of Things (IoT) applications to big data analytics. While computing resources available to implement these algorithms have become more powerful, both in terms of the complexity of problems that can be solved and …

    njit Repository record for Bio-inspired learning and hardware acceleration with emerging memories (opens in a new tab)

  16. Energy Efficient Spiking Neuromorphic Architectures for Pattern Recognition

    There is a growing concern over reliability, power consumption, and performance of traditional Von Neumann machines, especially when dealing with complex tasks like pattern recognition. In contrast, the human brain can address such problems with great ease. Brain-inspired neuromorphic computing has …

    tamu Repository record for Energy Efficient Spiking Neuromorphic Architectures for Pattern Recognition (opens in a new tab)

  17. EMERGING MEMORY-BASED DESIGNS AND RESILIENCY TO RADIATION EFFECTS IN ICS

    … scaling due to advancements in the modern semiconductor industry. However, the power efficiency along with reliability does not scale linearly with performance efficiency. High leakage and standby power in sub 100 nm technology are critical challenges faced by circuit designers. Recent …

    siu-theses Repository record for EMERGING MEMORY-BASED DESIGNS AND RESILIENCY TO RADIATION EFFECTS IN ICS (opens in a new tab)

  18. An advanced neuromorphic accelerator on FPGA for next-G spectrum sensing

    In modern communication systems, it’s important to detect and use available radio frequencies effectively. However, current methods face challenges with complexity and noise interference. We’ve developed a new approach using advanced artificial intelligence (AI) based computing techniques to …

    vt Repository record for An advanced neuromorphic accelerator on FPGA for next-G spectrum sensing (opens in a new tab)