A developers guide to Machine Learning
summary
Begins with practical steps: frame a sharp question, gather and clean data, transform features, pick algorithms, train and test, deploy. Demonstrates with Swedish house sales (~6,000 rows), visualizes scatterplots, removes outliers, turns zip and GPS into usable features, compares linear regression (predicts 4.8M actual vs 5.1M predicted) and decision forest, and deploys the chosen model as a REST web service using Azure ML Studio; also covers Jupyter, Kaggle/UCI datasets and when to use transfer learning versus cognitive services.
AI-written summary · about
chapters (28)
- 0:00Start
- 2:53Build Your Own Neural Networks
- 3:48Cognitive Services
- 4:48Transfer Learning
- 5:08Custom Models
- 6:57Scatter Plot
- 8:16Linear Regression
- 8:38Fitting the Model
- 9:48Confidence Interval
- 12:20Different Questions That You Can Ask Machine Learning
- 13:22Anomaly Detection
- 15:00Unsupervised Learning
- 16:35Reinforcement Learning
- 18:02Kaggle and Uci
- 24:55Duplicate Observations
- 26:13Missing Data
- 28:58Jupiter Notebooks
- 29:21Jupiter Notebooks
- 32:15Structural Problems
- 36:38Loss Function
- 37:18Gradient Descent
- 38:17Linear Regression Algorithm
- 38:46Classification
- 40:40Logistic Regression
- 41:38Neural Network
- 44:20Decision Trees
- 53:52Decision Tree
- 55:08Linear Regression Model
related talks
01h 02mA developers guide to Machine Learning
01h 05mAzure Machine Learning for the Developer
50mBuilding Intelligent Mobile Apps using Machine Learning
37mForecasting using machine learning methods
49mMachine Learning Exposed: Introduction to Machine Learning
50mBuilding Intelligent Mobile Apps using Machine Learning
51mMachine Learning Exposed Introduction to Machine Learning
54mMachine Learning for Developers