Sökning: "Jim Öhman"

Hittade 2 uppsatser innehållade orden Jim Öhman.

  1. 1. Application of Deep Q-learning for Vision Control on Atari Environments

    Master-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik

    Författare :Jim Öhman; [2021]
    Nyckelord :Reinforcement learning; Atari 2600; Deep Q-learning; Myopic Agents; Vision Control; Physics and Astronomy;

    Sammanfattning : The success of Reinforcement Learning (RL) has mostly been in artificial domains, with only some successful real-world applications. One of the reasons being that most real-world domains fail to satisfy a set of assumptions of RL theory. LÄS MER

  2. 2. Trainable Activation Functions For Artificial Neural Networks

    Kandidat-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik; Lunds universitet/Institutionen för astronomi och teoretisk fysik

    Författare :Jim Öhman; [2018]
    Nyckelord :ANN; ARTIFICIAL NEURAL NETWORKS; ACTIVATION FUNCTIONS; REGULARIZATION; Science General;

    Sammanfattning : Artificial Neural Networks (ANNs) are widely used information processing algorithms based roughly on biological neural networks. These networks can be trained to find complex patterns in datasets and to produce certain output signals given a set of input signals. LÄS MER