Sökning: "one-shot learning"
Visar resultat 1 - 5 av 9 uppsatser innehållade orden one-shot learning.
1. Design and Evaluation of Peptide Binders : In silico evaluation and comparison of generative AI for de novo peptide binder design
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Beräkningsbiologi och bioinformatikSammanfattning : Peptide binders are short proteins that bind to larger proteins. Due to peptide binders having high specificity and being cheap to synthesize, they are a prime candidate for drug design. Creating new proteins in silico can be divided into three steps: protein backbone generation, sequence design, and computational filtering. LÄS MER
2. Privacy Preserving Biometric Multi-factor Authentication
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : This thesis investigates the viability of using Fully Homomorphic Encryption and Machine Learning to construct a privacy-preserving biometric multi-factor authentication system. The system is based on the architecture described as ”Model K - Store distributed, compare distributed” in ISO/IEC 24745:2022 and uses the Torus Fully Homomorphic Encryption scheme proposed by Chillotti et al. LÄS MER
3. Defect classification in LPBF images using semi-supervised learning
Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013); Karlstads universitet/Avdelningen för datavetenskapSammanfattning : Laser powder bed fusion is an additive manufacturing technique that is capable of building metallic parts by spreading many layers of metal powder over a build surface and using a laser to melt specific sections of the surface. The part is built by melting consecutive layers on top of each other until the design is completed. LÄS MER
4. OSPREY: Person Re-Identification in the sport of Padel : Utilizing One-Shot Person Re-identification with locally aware transformers to improve tracking
Master-uppsats, Jönköping University/Jönköping AI Lab (JAIL)Sammanfattning : This thesis is concerned with the topic of person re-identification. Many tracking algorithms today cannot keep track of players reentering the scene from different angles and times. Therefore, in this thesis, current literature is explored to gather information about the topic, and a current state-of-the-art model is tested. LÄS MER
5. One-shot learning through generalized representations with neural networks
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Despite the rapid progress in the field of machine learning and artificial neural networks, many hurdles yet remain before machines can match human capabilities. One such hurdle is the copious amount of data required for these learning machines to reach adequate performance. LÄS MER