Sökning: "Inside the Black Box"
Visar resultat 6 - 10 av 14 uppsatser innehållade orden Inside the Black Box.
6. Design, synthesis and characterization of Dimethylammonium / Ethylammonium / Cesium Lead Halide Perovskites for optoelectronic applications
Kandidat-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)Sammanfattning : The world is facing a climate crisis and to be able to solve it society needs to decrease the use of fossil fuels and find renewable alternatives. Solar energy is a great contender for a renewable energy source since it can be harvested for eternal time. LÄS MER
7. Transformation of UML State Machine Diagram into Graph Database to Generate Test Cases
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : The manual approach in software testing is considered as expensive, error-prone, and time-consuming activity since it depends highly on the test engineers. As well, the process of software testing requires proper planning and resources to design the test cases. LÄS MER
8. Gottsunda culturehouse
Magister-uppsats, KTH/ArkitekturSammanfattning : The purpose of this project was to design a Culturehouse in Gottsunda Uppsala.The new culturehouse in Gottsunda started from a form bearing function concept. It is situated in the heart of Gottsunda centrum Uppsala regioen, where all the public communications and locals meet. LÄS MER
9. Lärocenter - publikt och privat
Kandidat-uppsats, KTH/ArkitekturSammanfattning : Utformandet av programmet kring ett nytt lärocentret vid Slakthusområdet har tagit sitt avstamp i ett ställningstagande kring vad ett lärocenter kan vara. I detta projekt har har avskildhet för studier prioriterats, som en mer klassisk tolkning av studiemiljö, samtidigt som behovet av en kulturell och transparent mötesplats beaktats. LÄS MER
10. Inside the Black Box: How to Explain Individual Predictions of a Machine Learning Model : How to automatically generate insights on predictive model outputs, and gain a better understanding on how the model predicts each individual data point.
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Machine learning models are becoming more and more powerful and accurate, but their good predictions usually come with a high complexity. Depending on the situation, such a lack of interpretability can be an important and blocking issue. LÄS MER