Machine learning in Action
summary
Hands-on ML pipeline that loads the Titanic dataset with pandas, drops unique IDs and names, imputes age with the median and embarked with the mode, applies StandardScaler, and runs hypothesis testing (t-test p < 0.05) to flag age as significant. Uses visualization with matplotlib/seaborn, builds a Keras sequential model with 128-64-1 dense layers, trains ~50 epochs and reports ~80% accuracy, noting the 61% non-survival class imbalance and using grid search for hyperparameter tuning.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:37Session overview
- 7:19Generative vs descriptive AI
- 16:24Titanic dataset exploration
- 23:14Exploratory data analysis with visualizations
- 39:35Feature significance testing
- 54:03Data cleaning steps
- 1:04:18Model training
- 1:17:51Model evaluation
- 1:22:09Summary
related talks
27mUsing Machine Learning to solve a classification problem with scikit-learn
54m"Would YOU Survive the Titanic?", with ML and .NET
39m"Would YOU Survive the Titanic?", with ML and .NET
51mHow to Test Artificial Intelligence and Machine Learning Solutions?
39mPredicting Titanic Survivors with Machine Learning
44mA Practical-ish Introduction to Data Science
50mBuilding Intelligent Mobile Apps using Machine Learning
50mBuilding Intelligent Mobile Apps using Machine Learning