This Specialization is taught by Andrew Ng, an AI visionary who has led critical research at Stanford University and groundbreaking work at Google Brain, Baidu, and Landing.AI to advance the AI field.
3-course Specialization:
- Supervised Machine Learning: Regression and Classification (1/*)
- Implementation of cost function and gradient descent
- Optimize a regression model using gradient descent
- Implementation of linear regression
- Feature scaling, feature engineering, and polynomial regression to improve model training
- Implementation of logistic regression for binary classification
- Address overfitting using regularization, to improve model performance
- Advanced Learning Algorithms (2/*)
- Get familiar with the diagram and components of a neural network
- Build a neural network in regular Python code (from scratch) to make predictions.
- Use a framework, TensorFlow, to build and train neural network
- Understanding activation functions (sigmoid, ReLu, linear, softmax)
- Diagnose, understand and adjust bias and variance in learning algorith
- training data improving
- measure precision and recall
- learn about variations of the decision tree, including random forests and boosted trees (XGBoost)
- Unsupervised Learning, Recommenders, Reinforcement Learning (3/*) - ongoing
- K-means clustering algorithm
- Anomaly detection
- Implementation of collaborative filtering recommender systems in TensorFlow
- Implementation of deep learning content based filtering using a neural network in TensorFlow
- Reinforcement learning
- Deep Q-learning nerual network
Course provides a broad introduction to modern machine learning
- supervised learning (multiple linear regression, logistic regression, neural networks, and decision trees),
- unsupervised learning (clustering, dimensionality reduction, recommender systems)
- the best practices used in Silicon Valley for artificial intelligence and machine learning innovation (evaluating and tuning models, taking a data-centric approach to improving performance, and more.)