Lecture 5: ML Projects (Full Stack Deep Learning - Spring 2021)
New course announcement ✨
We're teaching an in-person LLM bootcamp in the SF Bay Area on November 14, 2023. Come join us if you want to see the most up-to-date materials building LLM-powered products and learn in a hands-on environment.
https://www.scale.bythebay.io/llm-workshop
Hope to see some of you there!
--------------------------------------------------------------------------------------------- In this video, you will learn how to set up Machine Learning projects like a pro. This includes an understanding of the ML lifecycle, an acute mind of the feasibility and impact, an awareness of the project archetypes, and an obsession with metrics and baselines.
An extensive summary of this lecture can be accessed in this document: https://docs.google.com/document/d/1AA-QEMxsPTygvBhrrrm_0KTYGBZ-dtHlyGY-00iN65s/edit?usp=sharing
00:00 - Introduction
01:45 - Why Do ML Projects Fail?
02:53 - Lecture Overview and Running Case Study
06:14 - Lifecycle (Thinking about the activities in an ML project)
12:53 - Prioritizing Projects (Assessing the feasibility and impact of the projects)
36:51 - Archetypes (Knowing the main categories of projects and implications for project management)
49:06 - Metrics (Picking a single number to optimize)
01:02:36 - Baselines (Figuring out if your model is performing well)
01:10:21 - Conclusion
Видео Lecture 5: ML Projects (Full Stack Deep Learning - Spring 2021) канала The Full Stack
We're teaching an in-person LLM bootcamp in the SF Bay Area on November 14, 2023. Come join us if you want to see the most up-to-date materials building LLM-powered products and learn in a hands-on environment.
https://www.scale.bythebay.io/llm-workshop
Hope to see some of you there!
--------------------------------------------------------------------------------------------- In this video, you will learn how to set up Machine Learning projects like a pro. This includes an understanding of the ML lifecycle, an acute mind of the feasibility and impact, an awareness of the project archetypes, and an obsession with metrics and baselines.
An extensive summary of this lecture can be accessed in this document: https://docs.google.com/document/d/1AA-QEMxsPTygvBhrrrm_0KTYGBZ-dtHlyGY-00iN65s/edit?usp=sharing
00:00 - Introduction
01:45 - Why Do ML Projects Fail?
02:53 - Lecture Overview and Running Case Study
06:14 - Lifecycle (Thinking about the activities in an ML project)
12:53 - Prioritizing Projects (Assessing the feasibility and impact of the projects)
36:51 - Archetypes (Knowing the main categories of projects and implications for project management)
49:06 - Metrics (Picking a single number to optimize)
01:02:36 - Baselines (Figuring out if your model is performing well)
01:10:21 - Conclusion
Видео Lecture 5: ML Projects (Full Stack Deep Learning - Spring 2021) канала The Full Stack
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
5. Metrics - ML Projects - Full Stack Deep LearningLab 1: Setup and Intro (Full Stack Deep Learning - Spring 2021)Lecture 4: Transfer Learning and Transformers (Full Stack Deep Learning - Spring 2021)Lab 05: Troubleshooting & Testing (FSDL 2022)Experiment Management (6) - Infrastructure and Tooling - Full Stack Deep LearningLab 08: Monitoring (FSDL 2022)How to tell if your machine learning project idea is feasibleLecture 7: Machine Learning Teams - Full Stack Deep Learning - March 20196. Baselines - ML Projects - Full Stack Deep LearningLab 1 - Introduction - Full Stack Deep LearningRoles (2) - ML Teams - Full Stack Deep LearningStorage (4) - Data Management - Full Stack Deep LearningLab 7 - Continuous Integration - Full Stack Deep LearningCI/Testing (3) - Testing & Deployment - Full Stack Deep LearningLecture 12: Research Directions (Full Stack Deep Learning - Spring 2021)Computing and GPUs (3) - Infrastructure & Tooling - Full Stack Deep LearningAll in One (8) - Infrastructure and Tooling - Full Stack Deep LearningWeb Deployment (5) - Testing & Deployment - Full Stack Deep LearningLab 4 - Experimenting on Real Handwriting - Full Stack Deep LearningLab 5 - Line Detection - Full Stack Deep LearningLab 2: CNNs and Synthetic Data - Full Stack Deep Learning - Spring 2021