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 14 of 14 for “"Neural Network Learning"”.

  1. Neural Network Learning for Time-Series Predictions Using Constrained Formulations

    … along with violation guided backpropagation to neural network learning for near noiseless time-series benchmarks, we achieve much improved prediction performance as compared to that of previous work, while using less parameters. For noisy time-series, such as financial time series, we have …

    uiuc Repository record for Neural Network Learning for Time-Series Predictions Using Constrained Formulations (opens in a new tab)

  2. Improved cuckoo search based neural network learning algorithms for data classification

    Artificial Neural Networks (ANN) techniques, mostly Back-Propagation Neural Network (BPNN) algorithm has been used as a tool for recognizing a mapping function among a known set of input and output examples. These networks can be trained with gradient descent back propagation. The algorithm is not …

    uthm Repository record for Improved cuckoo search based neural network learning algorithms for data classification (opens in a new tab)

  3. Neuromorphic deep convolutional neural network learning systems for FPGA in real time

    Deep Learning algorithms have become one of the best approaches for pattern recognition in several fields, including computer vision, speech recognition, natural language processing, and audio recognition, among others. In image vision, convolutional neural networks stand out, due to their …

    sevilla Repository record for Neuromorphic deep convolutional neural network learning systems for FPGA in real time (opens in a new tab)

  4. Characterizing the Energy Requirement of Computer Vision

    The energy requirements of neural network learning are growing at a rapid rate. Increased energy demands have caused a global need to seek ways to improve energy efficiency of neural network learning. This thesis aims to establish a baseline on how adjusting basic parameters can affect energy …

    mit Repository record for Characterizing the Energy Requirement of Computer Vision (opens in a new tab)

  5. New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays

    A new neural network learning algorithm, called the Umbrella Algorithm, is developed and analysed. Its generalization, which does not exhibit over-specialisation, is observed in the EXOR problem and in an artificial data discrimination (Toy Data) problem. The learning time is found to be about 1/15 …

    concordia Repository record for New algorithm for neural network data discrimination applied to Markarian 421 high energy gamma rays (opens in a new tab)

  6. PACKET FILTER APPROACH TO DETECT DENIAL OF SERVICE ATTACKS

    … quantity of packets or connections to crash its network resources, bandwidth, equipment, or servers. Packet filtering methods are the most known way to prevent these attacks via identifying and blocking the spoofed attack from reaching its target. In this project, the extent of the DoS attacks …

    csusb Repository record for PACKET FILTER APPROACH TO DETECT DENIAL OF SERVICE ATTACKS (opens in a new tab)

  7. Information fusion schemes for real time risk assessment in adaptive control systems

    … Flight Control System (IFCS) deploys a neural network for in-flight aircraft failure accommodation. Verification and validation (V&V) of adaptive systems is a challenging research problem. Our approach to V&V relies on real-time monitoring of neural network learning. Monitors detect …

    wvu Repository record for Information fusion schemes for real time risk assessment in adaptive control systems (opens in a new tab)

  8. Learning, Reasoning, and Planning with Relational and Temporal Neural Networks

    … an overview of a neuro-symbolic framework for learning, reasoning, and planning with relational and temporal neural networks. The key idea is to exploit a structural bias in neural network learning that enables us to describe complex relational-temporal events and actions. These structures form …

    mit Repository record for Learning, Reasoning, and Planning with Relational and Temporal Neural Networks (opens in a new tab)

  9. Adaptive function modal learning neural networks

    Modal learning method is a neural network learning term that refers to a single neural network which combines with more than one mode of learning. It aims to achieve more powerful learning results than a neural network combines with only one single mode of learning. This thesis introduces a novel …

    london-metro Repository record for Adaptive function modal learning neural networks (opens in a new tab)

  10. Neural Networks for Music Emotion Recognition and Social Tags Emotion Representation

    … contributed to this area. With the emergence of neural networks, MER research has evolved from traditional machine learning methods combined with acoustic features to neural network learning methods combined with multi-source features. However, research gaps still exist in the following aspects. …

    uts Repository record for Neural Networks for Music Emotion Recognition and Social Tags Emotion Representation (opens in a new tab)

  11. Symbolic and connectionist machine learning techniques for short-term electric load forecasting

    This work applies connectionist neural network learning techniques and symbolic machine learning techniques to the problem of short-term electric load forecasting. The short-term electric load forecasting problem considered here is the prediction of bus loads one day ahead. The forecast quantities …

    vt Repository record for Symbolic and connectionist machine learning techniques for short-term electric load forecasting (opens in a new tab)

  12. Achieving Near-Natural Locomotion in Transfemoral Amputees - A Control Theoretic Approach

    Amputation of the lower limb is prescribed to address conditions such as trauma, vascular issues, tumors, neuropathy, frostbite, and complications from diabetes. Post-surgery, the individual has to be fitted with a prosthetic limb to regain mobility. While a good-fitting, well-designed prosthetic …

    unr Repository record for Achieving Near-Natural Locomotion in Transfemoral Amputees - A Control Theoretic Approach (opens in a new tab)

  13. Predikce deště z meteoradaru

    Tato práce se zabývá předpovědí počasí s využitím meteoradarových snímků a některých dalších souvisejících faktorů prostřednictvím výpočetního modelu neuronové sítě. Klade si za cíl prozkoumat možnosti predikce pomocí tohoto modelu a experimentálně stanovit co nejúspěšnější konfiguraci modelu pro …

    brno-tech Repository record for Predikce deště z meteoradaru (opens in a new tab)