Using Machine Learning and Not Dying Trying
summary
An introduction to what machine learning is and which techniques exist (supervised, unsupervised, reinforcement), including key concepts like overfitting, models and neural networks. It surveys practical technologies available to companies, shows examples to determine whether problems need large clusters or can run on a desktop with big files, and answers business-oriented questions: Do I need ML, what can it add to my product or user experience, and what infrastructure is required.
AI-written summary · about
chapters (16)
- 0:00Welcome
- 1:31What is ML
- 3:52ML learning phases
- 7:50ML learning types
- 13:02ML for SMEs
- 16:35ML infrastructure
- 18:03Data collection
- 20:33Data cleaning
- 22:50Key algorithm elements
- 28:51Classification algorithms
- 31:09Linear regression trees
- 34:50Decision trees random forest
- 37:58Unsupervised learning
- 40:49Python example
- 47:10ML tech frameworks
- 48:36Conclusion next steps
related talks
52mMachine learning: from practice to theory
44mHow to Improve UX with Machine Learning: Insights and learnings until now
39mMachine Learning for Developers
51mMachine Learning Exposed Introduction to Machine Learning
01h 21mIntroduction to Machine Learning for Software Engineers
40mWhat is Machine Learning, and How Do I Get Started?
35mML & I
59mMachine Learning: The End of Business Logic?