Fast Training of Generalizable Deep Neural Networks- [electronic resource]
Fast Training of Generalizable Deep Neural Networks- [electronic resource]
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214101242
- ISBN
- 9798379725426
- DDC
- 004
- 서명/저자
- Fast Training of Generalizable Deep Neural Networks - [electronic resource]
- 발행사항
- [S.l.]: : University of California, Los Angeles., 2023
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2023
- 형태사항
- 1 online resource(189 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
- 주기사항
- Advisor: Pottie, Gregory J.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2023.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약Effective natural agents excel in learning representations of our world and efficiently generalizing to make decisions. Critically, developing such advanced reasoning capabilities can occur even with limited information-rich samples. In stark contrast, the major success of deep learning-based artificial agents is primarily trained on massive datasets. This dissertation focuses on curvature-informed learning and generative modeling methods that boost efficiency and close the gap between natural and artificial agents, thus enabling computationally efficient and improved reasoning.This dissertation is comprised of two parts. First, we formally lay the foundations for learning. The goal is to establish optimization techniques, understand datasets, establish probabilistic generative models, and provide natural learning objectives even in settings with limited supervision. We discuss various first and second-order optimization methods, show the importance of modeling distributions in Variational Auto Encoders (VAEs),and discuss which points are essential for generalization in supervised learning. Building on these insights, we develop new algorithms to boost the performance of state-of-the-art models, select subsets to improve data quality, speed up training, mitigate their biases, and generate new augmentations on large labeled and partially labeled datasets. These contributions enable ML systems to better model and generalize to unseen and potentially out-of-distribution samples while drastically reducing training time and computational cost.
- 일반주제명
- Computer science.
- 일반주제명
- Computer engineering.
- 키워드
- Computer vision
- 키워드
- Machine learning
- 기타저자
- University of California, Los Angeles Electrical and Computer Engineering 0333
- 기본자료저록
- Dissertations Abstracts International. 84-12B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.