Essays about: "sequential training"

Showing result 6 - 10 of 40 essays containing the words sequential training.

1. 6. Can Wizards be Polyglots: Towards a Multilingual Knowledge-grounded Dialogue System

   University essay from Uppsala universitet/Institutionen för lingvistik och filologi

   Author : Evelyn Kai Yan Liu; [2022]
   Keywords : Knowledge-grounded dialogue; Dialogue systems; Generative question answering; Multilingual question answering; Multilingual dialogue systems; Transfer learning; Multi-task learning; Sequential training; Conversational AI; Natural Language Processing NLP ; Deep learning; Machine learning;

   Abstract : The research of open-domain, knowledge-grounded dialogue systems has been advancing rapidly due to the paradigm shift introduced by large language models (LLMs). While the strides have improved the performance of the dialogue systems, the scope is mostly monolingual and English-centric. READ MORE

3. 7. Attention-based Multi-Behavior Sequential Network for E-commerce Recommendation

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Zilong Li; [2022]
   Keywords : Recommendation System; Sequential Recommendation; Click-through Rate Model; Transformer; Multi-Task Learning; Sistema di Raccomandazione; Raccomandazione Sequenziale; Modello di Percentuale di Clic; Trasformatore; Apprendimento Multitasking; Rekommendationssystem; Sekventiell rekommendation; Klickfrekvensmodell; Transformator; Multi-Task Learning;

   Abstract : The original intention of the recommender system is to solve the problem of information explosion, hoping to help users find the content they need more efficiently. In an e-commerce platform, users typically interact with items that they are interested in or need in a variety of ways. For example, buying, browsing details, etc. READ MORE

4. 8. Continual Learning and Biomedical Image Data : Attempting to sequentially learn medical imaging datasets using continual learning approaches

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Davit Soselia; [2022]
   Keywords : Deep Learning; Continual Learning; Catastrophic Forgetting; Biomedical Image Classification; Djup inlärning; kontinuerligt lärande; katastrofal glömska; biomedicinsk bildklassificering;

   Abstract : While deep learning has proved to be useful in a large variety of tasks, a limitation remains of needing all classes and samples to be present at the training stage in supervised problems. This is a major issue in the field of biomedical imaging since keeping samples in the training sets consistently is often a liability. READ MORE

5. 9. Labeling audio through Games with a Purpose : The implementation of an efficient and enjoyable way of audio labeling with the help of sound cocktails

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Gustav Bergkvist; Hugo Jönsson; [2022]
   Keywords : ;

   Abstract : Audio labeling is a process that is yet too complicated to be entirely automated. Many forms of automated labeling are possible, though they require basic labels to get started. With data that has labels, training of a model is possible which potentially could unlock millions of hours to use. READ MORE

6. 10. Self-Supervised Learning: Land Classification of Satellite Imagery

   University essay from Lunds universitet/Matematisk statistik

   Author : Robert Skoglund; [2022]
   Keywords : Self-supervised learning; remote sensing; land classification; SimCLR; Mathematics and Statistics;

   Abstract : The rise of self-supervised learning has granted a deeper level of generalized machine learning capable of learning semantic representations without any use of labelling. With 700 satellites orbiting Earth and generating terabytes of unlabelled data daily, satellite imagery serves as a particularly enticing data set for self-supervised learning, containing rich information with many applicable domains,such as agriculture. READ MORE