100DaysOfMLCode
Outlines the 100DaysOfMLCode challenge: a public pledge to study or code ML for one hour daily over 100 days.
What this file does
Outlines the 100DaysOfMLCode challenge: a public pledge to study or code ML for one hour daily over 100 days.
When to use it
- Starting a structured machine learning learning streak
- Joining a public accountability challenge for ML
- Finding project ideas and learning resources for ML beginners
- Encouraging community engagement around ML practice
100DaysOfMLCode
Overview
These are the instructions for this video on Youtube by Siraj Raval for the #100DaysofMLCode Challenge.
Motivation
Machine Learning is the most transformative technology of our time. Whether its helping us discover new drugs for major diseases, fighting fraud, generating music, improving supply chain efficiency, the list of applications are truly endless. In order for us as a community to be able to make valuable contributions to the world, we need to master this technology. This is a call to action, a battle cry, a spark that will light a movement to radically improve the state of humanity. 100 Days of ML Code is a committment to better your understanding of this powerful tool by dedicating at least 1 hour of your time everyday to studying and/or coding machine learning for 100 days.
Eligibility
- Everyone is eligible, even people who've never coded before
The 3 Rules
- Make a public pledge to code or study machine learning for minimum 1 hour every day for the next 100 days via your favorite social platform using the #100DaysofMLCode Hashtag.
- Make a public log of your work. Update it daily. Here is a GitHub example template. Another one is here. You can also make a blog or vlog.
- If you see someone make a post using the #100DaysofMLCode hashtag, encourage them via a 'like', 'share', or comment!
Project Ideas
-
Siraj's pick is Preventing the Spread of Dengue Fever. The task is to predict the number of dengue cases each week (in each location) based on environmental variables describing changes in temperature, precipitation, vegetation, and more. An understanding of the relationship between climate and dengue dynamics can improve research initiatives and resource allocation to help fight life-threatening pandemics. You can literally save lives with machine learning.
-
There are many other projects out there though. Pick an industry that excites you, find a problem they have, locate a relevant dataset, apply AI to that dataset, and monetize the solution.
Learning Resources
Awards
- Siraj Raval will give a shoutout to some of the Wizards who succesfully complete the challenge, notify him if you've completed it via Twitter @sirajraval
- By the end of 100 days, you'll be expected to have a project you've contributed to, whether your own or another. The more impact you've had, the more likely you'll get a shoutout. Impact comes in the form of good documentation of your journey so that others can follow, a project that improves the lives of other people, or real progress in your own ability to code machine learning.
What's inside
7 sections: overview, motivation, eligibility, 3 rules, project ideas, learning resources, awards.
Change this for your project
- Replace
https://www.youtube.com/watch?v=cuQMBj1cWPo&t=7swith your own reference video URL - Replace
https://twitter.com/sirajravalwith your own social handle for notifications - Replace
https://gist.github.com/llSourcell/43194e486a92532bc343f7837b178edawith your own log template - Replace
https://github.com/LordSomen/100DaysOfML/blob/master/Log.mdwith your own example log
Where it goes
Keep it in your repository where the agent or team that needs it will read it.
Worth borrowing
- Public pledge with a daily minimum time commitment
- Daily public log to track progress and build accountability
- Community encouragement rule to foster engagement
Related Documents
How you work
Defines personality, planning, task execution, and communication conventions for a coding agent in the Codex CLI environment.
How you work
Defines personality, planning, task execution, and communication guidelines for a coding agent in Codex CLI.
内置 Agent 提示词
Documents the system prompts, tool permissions, and model assignments for six built-in subagents in Claude Code.
perplexity-ai_20250112
Defines the system prompt for Perplexity AI, instructing the assistant on how to answer queries using search results with strict formatting, citation, and query-type rules.