這個課程涵蓋了兩個不需要標記數據的深度學習領域:深度生成模型(Deep Generative Models)和自主學習(Self-supervised Learning)。近年來生成模型的發展使得對高維原始數據建模成為可能,如自然圖像、音檔和文本語料庫等。
14 週由深入淺拆解「深度學習」基礎、應用
自監督學習的進步已經開始縮小監督表示學習和非監督表示學習之間的差距,對看不見的任務進行微調。
課程涵蓋了這兩類領域的理論基礎和最新的應用,一共有 14 周,每周的課程都有相應的 PDF 課件和 YouTube 講課影片。
直接來看課程目錄
Week 1 (1/30)
Lecture 1a: Logistics
Lecture 1b: Motivation
Lecture 1c: Likelihood-based Models Part I: Autoregressive Model
Week 2 (2/6)
Lecture 2a: Likelihood-based Models Part I: Autoregressive Models (ctd) (same slides as week 1)
Lecture 2b: Lossless Compression
Lecture 2c: Likelihood-based Models Part II: Flow Models
Week 3 (2/13)
Lecture 3a: Likelihood-based Models Part II: Flow Models (ctd) (same slides as week 2)
Lecture 3b: Latent Variable Models – part 1
Week 4 (2/20)
Lecture 4a: Latent Variable Models – part 2
Lecture 4b: Bits-Back Coding
Week 5 (2/27)
Lecture 5a: Latent Variable Models – wrap-up (same slides as Latent Variable Models – part 2)
Lecture 5b: ANS coding (same slides as bits-back coding)
Lecture 5c: Implicit Models / Generative Adversarial Networks
Week X (3/6)
Final Project Discussion
Week 6 (3/13)
Lecture 6a: Implicit Models / Generative Adversarial Networks (ctd) (same slides as 5c)
Lecture 6b: Non-Generative Representation Learning [UPDATED 3/24]
Week 7 (3/20)
Lecture 7: Non-Generative Representation Learning (same slides as 6b)
Week 8 (4/3)
Lecture 8a: Strengths/Weaknesses of Unsupervised Learning Methods Covered Thus Far
Lecture 8b: Semi-Supervised Learning
Lecture 8c: Guest Lecture by Ilya Sutskever
Week 9 (4/10)
Lecture 9a: Unsupervised Distribution Alignment
Lecture 9b: Guest Lecture by Alyosha Efros
Week 10 (4/17)
Lecture 10: Language Models (Alec Radford)
Week 11 (4/24)
Lecture 11: Representation Learning in Reinforcement Learning
Week 12 (5/1)
Lecture 12: Guest Lecture by Aaron van den Oord [slides not available]
Week 13 (5/8)
RRR week: no lecture
Week 14 (5/15)
Final Project Presentations
OpenAI 科學家手把手教學
講解這門課程的一共有四位:
第一位是 Pieter Abbeel,他是柏克萊機器學習實驗室主任,柏克萊人工智慧研究實驗室(BAIR)聯合主任,還是 OpenAI 的科學家兼顧問;
第二位 Peter Chen 是 Pieter Abbeel 教授組裡的博士研究生,也是 OpenAI 的研究員;
其餘兩位 Jonathan Ho 和 Aravind Srinivas 也都是 Pieter Abbeel 教授組裡的博士研究生。