Sökning: "svart låda"
Visar resultat 1 - 5 av 25 uppsatser innehållade orden svart låda.
1. Computational study of the photophysical properties of two related photosensitizer proteins
Master-uppsats, KTH/KemiSammanfattning : Den ökande koldioxidhalten i atmosfären har lett till ett ökat intresse för användning av solljus, ett exempel är inom kemi. Att använda ljus i kemi kan leda till nya och intressanta kemiska reaktioner och kan tillämpas i användningsområden som exempelvis fotokatalys och fotovoltaik. LÄS MER
2. Explainable Reinforcement Learning for Gameplay
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : State-of-the-art Machine Learning (ML) algorithms show impressive results for a myriad of applications. However, they operate as a sort of a black box: the decisions taken are not human-understandable. LÄS MER
3. XAI-assisted Radio Resource Management: Feature selection and SHAP enhancement
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : With the fast development of radio technologies, wireless systems have become more convoluted. This complexity, accompanied by an increase of the number of connections, is translated into a need for more parameters to analyse and decisions to take at each instant. LÄS MER
4. Explainable Reinforcement Learning for Remote Electrical Tilt Optimization
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Controlling antennas’ vertical tilt through Remote Electrical Tilt (RET) is an effective method to optimize network performance. Reinforcement Learning (RL) algorithms such as Deep Reinforcement Learning (DRL) have been shown to be successful for RET optimization. LÄS MER
5. Exploring attribution methods explaining atrial fibrillation predictions from sinus ECGs : Attributions in Scale, Time and Frequency
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep Learning models are ubiquitous in machine learning. They offer state-of- the-art performance on tasks ranging from natural language processing to image classification. The drawback of these complex models is their black box nature. It is difficult for the end-user to understand how a model arrives at its prediction from the input. LÄS MER