Sökning: "black boxes"
Visar resultat 1 - 5 av 28 uppsatser innehållade orden black boxes.
1. Influence of Varying Electric Light Distribution on Melanopic Equivalent Daylight Illuminance and Lighting Energy Use
Master-uppsats, Lunds universitet/Institutionen för arkitektur och byggd miljö; Lunds universitet/Avdelningen för Energi och byggnadsdesignSammanfattning : Human beings in modern society spend more than 90% of their time indoors to live, work, and socialize. To improve health, quality of life and task performance, integrative lighting is designed to give the right light at the right time at the eye to stimulate circadian entrainment. LÄS MER
2. Applications of Formal Explanations in ML
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The most performant Machine Learning (ML) classifiers have been labeled black-boxes due to the complexity of their decision process. eXplainable Artificial Intelligence (XAI) methods aim to alleviate this issue by crafting an interpretable explanation for a models prediction. LÄS MER
3. A Study on Fault Tolerance of Object Detector Implemented on FPGA
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Objektdetektering har fått stort forskningsintresse de senaste åren, eftersom det är maskiners ögon och är en grundläggande uppgift inom datorseende som syftar till att identifiera och lokalisera föremål av intresse. Hårdvaruacceleratorer syftar vanligtvis till att öka genomströmningen för realtidskrav samtidigt som energiförbrukningen sänks. LÄS MER
4. Digital Literacy Through Design : Self-explanatory Devices by Use of Form
Kandidat-uppsats, Malmö universitet/Institutionen för konst, kultur och kommunikation (K3)Sammanfattning : Everyday technology is easier than ever to use and harder than ever to misuse, for this, we can attribute credits to how user friendly and error-proof minimal and autonomous artefacts are today. However, this puts a significant distance between users and the inner workings of their artefacts, the artefacts have become almost completely opaque black boxes. LÄS MER
5. Assessing BERT-Style Models' Abilities to Learn the Number of a Subject
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : There is an increasing interest in using deep neural networks in various downstream natural language processing tasks. Such models are commonly used as black boxes, meaning that their decision-making is difficult to interpret. In order to build trust in models, it is crucial to analyse their inner workings which lead to predictions. LÄS MER