Sökning: "Ann Nn"
Hittade 4 uppsatser innehållade orden Ann Nn.
1. A comparative study of Neural Network Forecasting models on the M4 competition data
Kandidat-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : The development of machine learning research has provided statistical innovations and further developments within the field of time series analysis. This study seeks to investigate two different approaches on artificial neural network models based on different learning techniques, and answering how well the neural network approach compares with a basic autoregressive approach, as well as how the artificial neural network models compare to each other. LÄS MER
2. Liability for Copyright Infringement: an investigation of the legal use of trained artificial neural networks in the context of copyright law.
Magister-uppsats, Lunds universitet/Juridiska institutionen; Lunds universitet/Juridiska fakultetenSammanfattning : The current thesis critically investigates whether training and using third-party data in artificial neural networks (ANNs) could constitute a liability for copyright infringement. Furthermore, the present paper sets out to explore whether training and using ANNs could fall within the IP right holders' exclusive rights. LÄS MER
3. The Machines are Coming Non-parametric methods and bankruptcy prediction - An artificial neural network approach
Master-uppsats, Göteborgs universitet/Graduate SchoolSammanfattning : Prediction of corporates bankruptcies is a topic that has gained more importance in the last two decades. Improvement in data accessibility makes the topic of bankruptcy prediction models a widely studied area. This study looks at bankruptcy prediction from a non-parametric perspective, with a focus on artificial neural networks (ANNs). LÄS MER
4. Comparative Analysis of Models for Real-Time Pattern Recognition
Kandidat-uppsats, Umeå universitet/Institutionen för matematik och matematisk statistikSammanfattning : The different applications for optical character recognition in real-time applications will most likely increase in the future as innovations as autonomous vehicles or elder care robots become a reality. This analysis therefore aims to evaluate different "off-the-shelf" models that can be used in these applications. LÄS MER