Advanced search

Showing result 1 - 5 of 174 swedish dissertations matching the above criteria.

  2. 1. Mind your Language, All Right? Performance-dependent neural patterns of language

    Author : Helene van Ettinger-Veenstra; Maria Engström; Peter Lundberg; Thomas Karlsson; Anita McAllister; Karsten Specht; Linköpings universitet; []
    Keywords : MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Language ability; performance; fMRI; functional magnetic resonance imaging; Broca; Wernicke; temporal lobe; inferior frontal gyrus; reading; fluency; lateralization; lateralisation; right hemisphere; performance-dependent; neural activation;

    Abstract : The main aim of this dissertation was to investigate the difference in neural language patternsrelated to language ability in healthy adults. The focus lies on unraveling the contributions of theright‐hemispheric homologues to Broca’s area in the inferior frontal gyrus (IFG) and Wernicke’s areain the posterior temporal and inferior parietal lobes. READ MORE

  4. 2. Neural Network Architecture Design : Towards Low-complexity and Scalable Solutions

    Author : Alireza M. Javid; Saikat Chatterejee; Alexandros Iosifidis; KTH; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Electrical Engineering; Elektro- och systemteknik;

    Abstract :  Over the past few years, deep neural networks have been at the center of attention in machine learning literature thanks to the advances in computational capabilities of modern graphical processing units (GPUs). This progress has made it possible to train large scale neural networks by using thousands, and even millions, of training samples to achieve outstanding estimation accuracy in various applications that were not simply possible before. READ MORE

  5. 3. High-Performance Network-on-Chip Design for Many-Core Processors

    Author : Boqian Wang; Zhonghai Lu; Kun-Chih Chen; KTH; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Network-on-Chip; Chip Multi Many-core Processors; Multiprocessor System-on-Chip; High-Performance Computing; Cache Coherence; Virtual Channel Reservation; Admission Control; Artificial Neural Network; AXI4; Quality of Service; Network-on-Chip; Chip Multi Many-core Processors; Multiprocessor Sys-tem on a Chip; High-Performance Computing; Cache Coherence; Virtual Channel Reser-vation; Admission Control; Artificial Neural Network; AXI4; Quality of Servic; Informations- och kommunikationsteknik; Information and Communication Technology;

    Abstract : With the development of on-chip manufacturing technologies and the requirements of high-performance computing, the core count is growing quickly in Chip Multi/Many-core Processors (CMPs) and Multiprocessor System-on-Chip (MPSoC) to support larger scale parallel execution. Network-on-Chip (NoC) has become the de facto solution for CMPs and MPSoCs in addressing the communication challenge. READ MORE

  6. 4. Performance Indicators. A performance prediction method for moisture safety design

    Author : Veronica Yverås; Chalmers tekniska högskola; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Artificial Neural Network; Performance prediction; Moisture safety;

    Abstract : The aims of this research project is to develop and gain knowledge about a different approach to moisture safety design based on AI in order to attain healthy buildings and relate this new approach to current practice and prospective users. Secondary data (data produced for some other purpose) was used to train Artificial Neural Networks (ANN) to predict the performance of outdoor ventilated crawl-spaces regarding microbiological smell, mould and rot. READ MORE

  7. 5. Network Parameterisation and Activation Functions in Deep Learning

    Author : Martin Trimmel; Matematik LTH; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; deep learning; linear region; network parameterisation; activation function; network calibration; conformal predictnio; tropical algebra; rational function; temperature scaling; network symmetries;

    Abstract : Deep learning, the study of multi-layered artificial neural networks, has received tremendous attention over the course of the last few years. Neural networks are now able to outperform humans in a growing variety of tasks and increasingly have an impact on our day-to-day lives. READ MORE