Machine learning: from practice to theory
summary
Overview of fundamental machine learning concepts and supervised learning techniques: defines what ML is and its uses, explains cost functions and optimization, overfitting, feature engineering, deep learning, and other common methods beyond neural networks so practitioners can better understand and apply ML models.
AI-written summary · about
chapters (16)
- 0:00Start
- 11:27System overview
- 12:32Classification vs. Regression
- 14:14Linear classifiers
- 26:53Artificial neural networks (ANN)
- 29:52Ensemble learning
- 31:18Overfitting and generalization
- 32:36Cross-validation
- 34:20Regularization
- 35:20The curse of dimensionality
- 36:38Feature engineering
- 37:58Feature extraction
- 38:46Feature selection
- 39:26Deep learning
- 44:08Deep neural networks (DNN)
- 46:02Deep belief networks (DBN)
related talks
49mUsing Machine Learning and Not Dying Trying
01h 24mWhat is Machine Learning?
37mDemystifying machine learning – from developer to ML engineer
01h 21mIntroduction to Machine Learning for Software Engineers
35mML & I
39mMachine Learning for Developers
40mWhat is Machine Learning, and How Do I Get Started?
51mMachine Learning Exposed Introduction to Machine Learning