-MITOCW-6.7960-Deep-Learning-Study

MITOCW 6.7960 Deep Learning을 수강하며 작성한 기록입니다.

1. 수업 필기

Details

# 📚 MIT 6.7960: Deep Learning (Fall 2024) - Lecture Index

Instructors: Prof. Phillip Isola, Prof. Sara Beery, Dr. Jeremy Bernstein
Source: MIT OpenCourseWare

---

📖 Table of Contents

Lecture	Topic	Slide PDF
01	Introduction to Deep Learning	PDF
02	How to Train a Neural Net	PDF
03	Approximation Theory	PDF
04	Architectures for Grids	PDF
05	Graph Neural Networks	PDF
06	Neural Network Generalization	PDF
07	Scaling Rules for Optimization	PDF
08	Transformers	PDF
09	Hacker's Guide to Deep Learning	PDF
10	Memory and Sequence Modeling	PDF
11	Representation Learning I	PDF
12	Similarity-Based Representation Learning	PDF
13	Architectural Bias on Representations	PDF
14	Deep Generative Models I	PDF
15	Deep Generative Models II	PDF
16	Deep Generative Models III	PDF
17	Out-of-Distribution Generalization	PDF
18	Transfer Learning I	PDF
19	Transfer Learning II	PDF
20	Scaling Laws	PDF
21	Language Models	PDF
22	Not Available	-
23	Metrized Deep Learning	PDF
24	Inference Methods for Deep Learning	PDF
25	Not Available	-

---

Note: Lectures 22 and 25 are omitted in the official OCW release.