Sökning: "continual learning"

Visar resultat 1 - 5 av 26 uppsatser innehållade orden continual learning.

1. 1. Utilizing energy-saving techniques to reduce energy and memory consumption when training machine learning models : Sustainable Machine Learning

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

   Författare :Khalid El Yaacoub; [2024]
   Nyckelord :Sustainable AI; Machine learning; Quantization-Aware Training; Model Distillation; Quantized Distillation; Siamese Neural Networks; Continual Learning; Experience Replay; Data Efficient AI; Energy Consumption; Energy-Savings; Sustainable ML; Computation resources; Hållbar maskin inlärning; Hållbar AI; Maskininlärning; Quantization-Aware Training; Model Distillation; Quantized Distillation; siamesiska neurala nätverk; Continual Learning; Experience Replay; Dataeffektiv AI; Energiförbrukning; Energibesparingar; Beräkningsresurser;

   Sammanfattning : Emerging machine learning (ML) techniques are showing great potential in prediction performance. However, research and development is often conducted in an environment with extensive computational resources and blinded by prediction performance. LÄS MER

3. 2. A Comparison of CNN and Transformer in Continual Learning

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

   Författare :Jingwen Fu; [2023]
   Nyckelord :Convolutional Neural Network; Transformer; Continual Learning; Image Classification; Faltade Neurala Nätverk; Transformator; Kontinuerligt Lärande; Bildklassificering;

   Sammanfattning : Within the realm of computer vision tasks, Convolutional Neural Networks (CNN) and Transformers represent two predominant methodologies, often subject to extensive comparative analyses elucidating their respective merits and demerits. This thesis embarks on an exploration of these two models within the framework of continual learning, with a specific focus on their propensities for resisting catastrophic forgetting. LÄS MER

4. 3. Integration of Continual Learning and Semantic Segmentation in a vision system for mobile robotics

   Master-uppsats, Luleå tekniska universitet/Rymdteknik

   Författare :Cristian David Echeverry Valencia; [2023]
   Nyckelord :Continual Learning; Progressive Neural Networks; mobile robotics; Computer Vision; Machine Learning; Semantic Segmentation;

   Sammanfattning : Over the last decade, the integration of robots into various applications has seen significant advancements fueled by Machine Learning (ML) algorithms, particularly in autonomous and independent operations. While robots have become increasingly proficient in various tasks, object instance recognition, a fundamental component of real-world robotic interactions, has witnessed remarkable improvements in accuracy and robustness. LÄS MER

5. 4. Machines Do Not Have Little Gray Cells: : Analysing Catastrophic Forgetting in Cross-Domain Intrusion Detection Systems

   Magister-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Ramin Valieh; Farid Esmaeili Kia; [2023]
   Nyckelord :Catastrophic Forgetting; Intrusion Detection Systems; Continual Learning;

   Sammanfattning : Cross-domain intrusion detection, a critical component of cybersecurity, involves evaluating the performance of neural networks across diverse datasets or databases. The ability of intrusion detection systems to effectively adapt to new threats and data sources is paramount for safeguarding networks and sensitive information. LÄS MER

7. 5. Tackling Non-Stationarity in Reinforcement Learning via Latent Representation : An application to Intraday Foreign Exchange Trading

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

   Författare :Adriano Mundo; [2023]
   Nyckelord :Reinforcement Learning; Latent Representation; VAE; Non-Stationary; FQI; FX Trading; Förstärkningsinlärning; Latent representation; VAE; Icke-stationär; FQI; FX handel;

   Sammanfattning : Reinforcement Learning has applications in various domains, but the typical assumption is of a stationary process. Hence, when this hypothesis does not hold, performance may be sub-optimal. LÄS MER