Search for dissertations about: "neural network: performance"

Showing result 1 - 5 of 100 swedish dissertations containing the words neural network: performance.

  1. 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 : MEDICAL AND HEALTH SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; 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

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

    Author : Alireza M. Javid; Saikat Chatterejee; Alexandros Iosifidis; KTH; []
    Keywords : ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; 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

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

    Author : Boqian Wang; Zhonghai Lu; Kun-Chih Chen; KTH; []
    Keywords : NATURAL SCIENCES; NATURVETENSKAP; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; NATURVETENSKAP; TEKNIK OCH TEKNOLOGIER; NATURAL SCIENCES; 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

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

    Author : Veronica Yverås; Chalmers University of Technology; []
    Keywords : 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

  5. 5. On Hardware Implementation of Discrete-Time Cellular Neural Networks

    Author : Suleyman Malki; Institutionen för elektro- och informationsteknik; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Circuit switching; Network on Chip; Vein feature extraction; Velocity measurement; Discrete-Time Cellular Neural Network; Switched broadcast; Serialized broadcast; Cellular Neural Network; Field- Programmable Gate-Array; Image processing.;

    Abstract : Cellular Neural Networks are characterized by simplicity of operation. The network consists of a large number of nonlinear processing units; called cells; that are equally spread in the space. READ MORE