Sökning: "Joey Öhman"

Hittade 2 uppsatser innehållade orden Joey Öhman.

1. 1. Active Learning for Named Entity Recognition with Swedish Language Models

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

   Författare :Joey Öhman; [2021]
   Nyckelord :Active learning; Named entity recognition; Language models; Natural language processing; Bert; Swedish; Aktiv inlärning; Namnigenkänning; Språkmodeller; Naturlig språkbehandling; Bert; Svenska;

   Sammanfattning : The recent advancements of Natural Language Processing have cleared the path for many new applications. This is primarily a consequence of the transformer model and the transfer-learning capabilities provided by models like BERT. However, task-specific labeled data is required to fine-tune these models. LÄS MER

3. 2. AlphaZero to Alpha Hero : A pre-study on Additional Tree Sampling within Self-Play Reinforcement Learning

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

   Författare :Fredrik Carlsson; Joey Öhman; [2019]
   Nyckelord :;

   Sammanfattning : In self-play reinforcement learning an agent plays games against itself and with the help of hindsight and retrospection improves its policy over time. Using this premise, AlphaZero famously managed to become the strongest known Go, Shogi, and Chess entity by training a deep neural network from data collected solely from self-play. LÄS MER