Sökning: "modular neural network"
Visar resultat 1 - 5 av 14 uppsatser innehållade orden modular neural network.
1. Quantifying the Impact of Synaptic Delay and Neuronal Refractory Period on Criticality in Hierarchical Modular Neural Networks
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Self-organized brain criticality suggests that the brain is able to operate near a critical point.With compelling evidence supporting the theory, it is important to understand whichbiological mechanisms are required for critical dynamics to occur. LÄS MER
2. Cooperative Modular Neural Networks for Artificial Intelligence in Games : A Comparison with A Monolithic Neural Network Regarding Technical Aspects and The Player Experience
Uppsats för yrkesexamina på avancerad nivå, Blekinge Tekniska Högskola/Fakulteten för datavetenskaperSammanfattning : Recent years have seen multiple machine-learning research projects concerning agents in video games. Yet, there is a disjoint between this academic research and the video game industry, evidenced by the fact that game developers still hesitate to use neural networks (NN) due to lack of clarity and control. LÄS MER
3. Inverse Uncertainty Quantification for Sounding Rocket Dispersion
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : Sounding rocket impact points are subject to dispersion due to uncertainties in simulation model parameters and perturbations of the rocket trajectory during flight. Estimating the area of dispersion assumes that associated model uncertainties and magnitude of perturbations have already been inferred. LÄS MER
4. Quality inspection of multiple product variants using neural network modules
Master-uppsats, Högskolan i Skövde/Institutionen för ingenjörsvetenskapSammanfattning : Maintaining quality outcomes is an essential task for any manufacturing organization. Visual inspections have long been an avenue to detect defects in manufactured products, and recent advances within the field of deep learning has led to a surge of research in how technologies like convolutional neural networks can be used to perform these quality inspections automatically. LÄS MER
5. Deep Reinforcement LearningA case study of AlphaZero
Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Using deep neural networks for reinforcement learning has proven very successful, as demonstrated by the AlphaZero algorithm developed by DeepMind in 2018. This algorithm is capable of mastering two-player zero-sum board games entirely by playing against itself. LÄS MER