Sökning: "nerual networks"

Hittade 3 uppsatser innehållade orden nerual networks.

  1. 1. Robotar som uppfinner? – en patenträttslig studie av uppfinnarskap i ljuset av AI:s ökande medverkan i uppfinningsprocessen

    Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Juridiska institutionen; Lunds universitet/Juridiska fakulteten

    Författare :Victor Ask; [2020]
    Nyckelord :immaterialrätt; Law and Political Science;

    Sammanfattning : Artificial intelligence (AI) is predicted to unleash a new industrial revolution, which is likely to leave no part of society untouched. Following the development of increasingly advanced AI-systems, patent offices around the world have begun to question the implications of this technology for the patent system. LÄS MER

  3. 2. Incremental Learning of Deep Convolutional Neural Networks for Tumour Classification in Pathology Images

    Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik

    Författare :Philip Johansson; [2019]
    Nyckelord :Deep Learning; Convolutional Nerual Networks; Pathology; Incremental Learning; Catastrophic Forgetting; Generative Adversarial Networks; Auxiliary Classification Generative Adversarial Networks;

    Sammanfattning : Medical doctors understaffing is becoming a compelling problem in many healthcare systems. This problem can be alleviated by utilising Computer-Aided Diagnosis (CAD) systems to substitute doctors in different tasks, for instance, histopa-thological image classification. LÄS MER

  4. 3. Predicting trajectories of golf balls using recurrent neural networks

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Anton Jansson; [2017]
    Nyckelord :predicting; extrapolating; trajectories; golf; golf balls; machine learning; nerual networks; rnn; recurrent neural networks; lstm; long short-term memory;

    Sammanfattning : This thesis is concerned with the problem of predicting the remaining part of the trajectory of a golf ball as it travels through the air where only the three-dimensional position of the ball is captured. The approach taken to solve this problem relied on recurrent neural networks in the form of the long short-term memory networks (LSTM). LÄS MER