Sökning: "transfer learning"

Visar resultat 31 - 35 av 661 uppsatser innehållade orden transfer learning.

1. 31. Novel Method of ASIC interface IP development using HLS

   Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

   Författare :Anestis Athanasiadis; Chandranshu Mishra; [2023]
   Nyckelord :High Level Synthesis; HLS; Untimed C ; Control logic; I3C; clock-accurate design; IP development; Technology and Engineering;

   Sammanfattning : High-Level Synthesis(HLS) is a design methodology that enables designers to implement hardware from high-level coding languages, such as C, C++, or System C. It provides designers with the ability to convey their design at a higher level of abstraction, which allows more emphasis on an algorithm and functional aspects of design instead on low-level hardware details. LÄS MER

3. 32. Aggregating predictions of a yeast semantic segmentation model : Reducing a pixel classifier into a binary image classifier

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ali Muquri; [2023]
   Nyckelord :;

   Sammanfattning : The introduction of machine learning in clinical microbiology is important for aiding clinical laboratories with highly repetitive tasks that are fatiguing, error-prone, and require long employee training time due to the complex nature of the task. A challenging task that belongs to the subareas that need assistance is yeast detection in fluorescence microscopy where various yeast morphologies exist. LÄS MER

4. 33. Automatic quality assessment of formed fiber products via Computer Vision and Artificial Intelligence

   Uppsats för yrkesexamina på grundnivå, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Jesper Sköld; [2023]
   Nyckelord :Artificial intelligence; Deep learning; CNN; YOLO; Computer Vision; Fiber products; Machine learning; Neural network;

   Sammanfattning : Defects on fiber products have varied appearances and are common in production lines. A reliable system that can classify and identify defects without subjectivity and fatigue can improve a company's quality management. Computer vision systems are crucial for any autonomous system, but accuracy is essential for real-life applications. LÄS MER

5. 34. Efficient Sentiment Analysis and Topic Modeling in NLP using Knowledge Distillation and Transfer Learning

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :George Malki; [2023]
   Nyckelord :Large Language Model; RoBERTa; Knowledge distillation; Transfer learning; Sentiment analysis; Topic modeling; Stor språkmodell; RoBERTa; Kunskapsdestillation; överföringsinlärning; Sentimentanalys; Ämnesmodellering;

   Sammanfattning : This abstract presents a study in which knowledge distillation techniques were applied to a Large Language Model (LLM) to create smaller, more efficient models without sacrificing performance. Three configurations of the RoBERTa model were selected as ”student” models to gain knowledge from a pre-trained ”teacher” model. LÄS MER

7. 35. Improving the accessibility of API documentation for non-technical users

   Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Författare :Gabriele Marinosci; Ratmir Shchadrynski; [2023]
   Nyckelord :REST API; API documentation; User Experience;

   Sammanfattning : Software documentation is one of the most important aspects of the software development process, as it allows the transfer of knowledge between individuals, regardless of their background and their technical knowledge. In particular, Application Programming Interfaces provide the basic structure for the communication and integration between different software systems. LÄS MER