What is Machine Learning?
summary
Defines machine learning by explaining its scientific foundations rather than implementation specifics, focusing on why availability of fast compute, cheap storage and relevant data enabled widespread ML use. Covers core concepts behind training models and what distinguishes machine learning from other approaches, aimed at listeners who encounter the term but lack a clear understanding. Does not go into algorithmic details or industrial applications.
AI-written summary · about
chapters (14)
- 0:00Start
- 6:25Why and how does something work?
- 7:55The Scientific Method
- 9:33Caveats
- 12:54How to guess the rules?
- 14:14What is Machine Learning?
- 15:32Terminology: Model
- 15:59Terminology: Learning
- 17:20Problem Statement
- 26:20Example
- 32:22Reinforcement Learning
- 39:56Unsupervised Learning
- 48:00What is modelling?
- 48:52Mathematical Modeling!
related talks
37mDemystifying machine learning – from developer to ML engineer
52mMachine learning: from practice to theory
39mMachine Learning for Developers
35mML & I
40mWhat is Machine Learning, and How Do I Get Started?
01h 21mIntroduction to Machine Learning for Software Engineers
49mUsing Machine Learning and Not Dying Trying
59mMachine Learning: The End of Business Logic?