NLP112 [2024-2] 김영중 - Seq2Seq(Sequence to Sequence Learning with Neural Networks) https://arxiv.org/abs/1409.3215 Sequence to Sequence Learning with Neural NetworksDeep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paparxiv.org Abstract Sequence-to-Sequence(Seq2Seq) 모델은 기존의 순환.. 2024. 12. 21. [2024-2] 이재호 - RNN, LSTM, GRU RNN, LSTM, GRU는 모두 순환신경망(Recurrent neural networks)의 변형으로 순차적인 데이터(sequence data)를 처리하기 위해 설계된 알고리즘입니다. 각각의 알고리즘의 아키텍처와 특징에 대해 알아보겠습니다. # Fundamentals of Recurrent Neural Network(RNN) and Long Short-Term Memory (LSTM) Network - Alex Sherstinsky (2018)https://arxiv.org/abs/1808.03314 Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) NetworkBecause of their effective.. 2024. 12. 13. [2024-2] 백승우 - Retrieval-Augmented Generation for Large Language Models: A Survey Retrieval-Augmented Generation for Large Language Models: A SurveyLarge Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution byarxiv.org0. AbstractLLM(Large Language Model)은 뛰어난 성과를 보이지만, hallucination, .. 2024. 11. 11. [2024-2] 백승우 - (RAG) Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksLarge pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limarxiv.org0. AbstractPretrained LLM은 사실의 지식을 매개변수에 저장하고, downstream NLP 작업에서 미.. 2024. 11. 3. 이전 1 ··· 20 21 22 23 24 25 26 ··· 28 다음
