2021. 5. 17. 09:37ㆍ미분류
작업 git-repository
https://github.com/FullStackDL-Study
Full Stack Deep Learning - Spring 2021
Week 1: Fundamentals
The week of February 1, we do a blitz review of the fundamentals of deep learning, and introduce the codebase we will be working on in labs for the remainder of the class.
- Lecture 1: DL Fundamentals - 21.05.18
- Notebook: Coding a neural net from scratch - 21.05.19
- Lab 1: Setup and Intro - 21.05.21
Reading:
How the backpropagation algorithm works - 21.05.21
Week 2: CNNs
The week of February 8, we cover CNNs and Computer Vision Applications, and introduce a CNN in lab.
- Lecture 2A: CNNs - 21.05.30
- Lecture 2B: Computer Vision Applications - 21.05.30
- Lab 2: CNNs - 21.05.30
Reading:
A brief introduction to Neural Style Transfer - 21.06.06
Improving the way neural networks learn - 21.06.19 Weight Initialization 부터
Week 3: RNNs
The week of February 15, we cover RNNs and applications in Natural Language Processing, and start doing sequence processing in lab.
- Lecture 3: RNNs - 21.06.19
- Lab 3: RNNs - 21.06.20
Reading:
The Unreasonable Effectiveness of Recurrent Neural Networks
Attention Craving RNNS: Building Up To Transformer Networks
Week 4: Transformers
The week of February 22, we talk about the successes of transfer learning and the Transformer architecture, and start using it in lab.
Reading:
Week 5: ML Projects
The week of March 1, our synchronous online course begins with the first "Full Stack" lecture: Setting up ML Projects.
- Lecture 5: Setting up ML Projects (👈 with detailed notes)
Reading:
ML Yearning (and subscribe to Andrew Ng's newsletter)
Those in the syncronous online course will have their first weekly assignment: Assignment 1, available on Gradescope.
Week 6: Infra & Tooling
The week of March 7, we tour the landscape of infrastructure and tooling for deep learning.
- Lecture 6: Infrastructure & Tooling (👈 with detailed notes)
Reading:
Machine Learning: The High-Interest Credit Card of Technical Debt
Those in the syncronous online course will have to work on Assignment 2.
Week 7: Troubleshooting
The week of March 14, we talk about how to best troubleshoot training. In lab, we learn to manage experiments.
- Lecture 7: Troubleshooting DNNs (👈 with detailed notes)
- Lab 5: Experiment Management
Reading:
Those in the syncronous online course will have to work on Assignment 3.
Week 8: Data
The week of March 21, we talk about Data Management, and label some data in lab.
- Lecture 8: Data Management (👈 with detailed notes)
- Lab 6: Data Labeling
Reading:
Emerging architectures for modern data infrastructure
Those in the syncronous online course will have to work on Assignment 4.
Week 9: Ethics
The week of March 28, we discuss ethical considerations. In lab, we move from lines to paragraphs.
- Lecture 9: AI Ethics (👈 with detailed notes)
- Lab 7: Paragraph Recognition
Those in the synchronous online course will have to submit their project proposals.
Week 10: Testing
The week of April 5, we talk about Testing and Explainability, and set up Continuous Integration in lab.
- Lecture 10: Testing & Explainability (👈 with detailed notes)
- Lab 8: Testing & CI
Those in the synchronous online course will work on their projects.
Week 11: Deployment
The week of April 12, we cover Deployment and Monitoring, and deploy our model to AWS Lambda in lab.
- Lecture 11: Deployment & Monitoring (👈 with detailed notes)
- Lab 9: Web Deployment
Those in the synchronous online course will work on their projects.
Week 12: Research
The week of April 19, we talk research, and set up robust monitoring for our model.
- Lecture 12: Research Directions (👈 with detailed notes)
- Lab 10: Monitoring
Those in the synchronous online course will work on their projects.
✨Week 13: Teams✨
The week of April 26, we discuss ML roles and team structures, as well as big companies vs startups.
- Lecture 13: ML Teams & Startups (👈 with detailed notes)
- Panel Discussion: Do I need a PhD to work in ML?
Week 14-16: Projects
Those in the synchronous online course will submit 5-minute videos of their projects and associated write-ups by May 15.
The week of May 17, we will award the best projects and host them on this site.
'미분류' 카테고리의 다른 글
| edwith 딥러닝 교육 목차 - (수강완료) (0) | 2020.11.09 |
|---|