Search for dissertations about: "neural systems"

Showing result 1 - 5 of 376 swedish dissertations containing the words neural systems.

  2. 1. On the Robustness of Statistical Models: Entropy-based Regularisation and Sensitivity of Boolean Deep Neural Networks

    Author : Olof Zetterqvist; Chalmers tekniska högskola; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Deep neural networks; Noise stability; Noisy labels; Noise sensitivity; Boolean functions; Regularisation;

    Abstract : Models like deep neural networks are known to be sensitive towards many different aspects of noise. Unfortunately, due to the black-box nature of these models, it is in general not known why this is the case. Here, we analyse and attack these problems from three different perspectives. READ MORE

  4. 2. Journeys in vector space: Using deep neural network representations to aid automotive software engineering

    Author : Dhasarathy Parthasarathy; Chalmers tekniska högskola; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; automotive software design and testing; generative adversarial networks; latent space arithmetic; generative AI; explainable AI; large language models;

    Abstract : Context - The automotive industry is in the midst of a transformation where software is becoming the primary tool for delivering value to customers. While this has vastly improved their product offerings, vehicle manufacturers are facing an urgent need to continuously develop, test, and deliver functionality, while maintaining high levels of quality. READ MORE

  5. 3. Applications of artificial neural networks for time series data analysis in energy domain

    Author : Fan Zhang; Hasan Fleyeh; Stawomir Nowaczyk; Högskolan Dalarna; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Deregulated energy market; electricity prices; district heating; energy efficiency; neural networks; Complex Systems – Microdata Analysis; Komplexa system - mikrodataanalys;

    Abstract : With the development of artificial intelligence techniques and increased installation of smart meters in recent years, time series analysis using historical data in the energy domain becomes applicable. In this thesis, microdata analysis approaches are used, which consist of data acquisition, data processing, data analysis and data modelling, aiming to address two research problems in the energy domain. READ MORE

  6. 4. Towards Supporting IoT System Designers in Edge Computing Deployment Decisions

    Author : Majid Ashouri; Paul Davidsson; Romina Spalazzese; Malmö universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Internet of Things; Edge computing; Decision Support; Quality Attrib-utes; Metrics; Simulation;

    Abstract : The rapidly evolving Internet of Things (IoT) systems demands addressing new requirements. This particularly needs efficient deployment of IoT systems to meet the quality requirements such as latency, energy consumption, privacy, and bandwidth utilization. READ MORE

  7. 5. Multi-LSTM Acceleration and CNN Fault Tolerance

    Author : Stefano Ribes; Chalmers tekniska högskola; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Compression; SVD; LSTMs; CNNs; Fault Tolerance; Machine Learning; FPGA; Roofline Model; HLS; Caffe;

    Abstract : This thesis addresses the following two problems related to the field of Machine Learning: the acceleration of multiple Long Short Term Memory (LSTM) models on FPGAs and the fault tolerance of compressed Convolutional Neural Networks (CNN). LSTMs represent an effective solution to capture long-term dependencies in sequential data, like sentences in Natural Language Processing applications, video frames in Scene Labeling tasks or temporal series in Time Series Forecasting. READ MORE