Applied Machine Learning (CS 460)

Outline

28 sections

1. 01Course Intro & Syllabus
2. 02Section 1: Introduction to Applied Machine Learning
3. 03Section 2: The Machine Learning Landscape
4. 04Section 3: Setting Up the Workspace & Data Processing Quick Start
5. 05Section 4: Data Preparation and Feature Engineering Pipelines
6. 06Section 5: Model Selection, Cross-Validation & Hyperparameter Tuning
7. 07Section 6: Linear Regression & Gradient Descent Optimization
8. 08Section 7: Regularized Models & Softmax Classifiers
9. 09Section 8: Image Classification & Performance Metrics
10. 10Section 9: Support Vector Machines
11. 11Section 10: Decision Trees
12. 12Section 11: Ensemble Learning & Boosting Algorithms
13. 13Section 12: Dimensionality Reduction & PCA
14. 14Section 13: Unsupervised Clustering & Density Estimation
15. 15Midterm Exam
16. 16Section 14: Introduction to ANNs and the Keras Sequential API
17. 17Section 15: Functional/Subclassing APIs and TensorBoard Visualizations
18. 18Section 16: Techniques for Training Deep Neural Networks
19. 19Section 17: Custom Models, Metrics & Autodiff in TensorFlow
20. 20Section 18: Loading & Preprocessing Data with the tf.data API
21. 21Section 19: Deep Computer Vision Using CNNs
22. 22Section 20: Processing Sequences Using RNNs, LSTMs & GRUs
23. 23Section 21: Natural Language Processing & Attention Mechanisms
24. 24Section 22: The Transformer Architecture and Pretrained Language Models
25. 25Section 23: Autoencoders, VAEs & Generative Adversarial Networks
26. 26Section 24: Deep Reinforcement Learning with OpenAI Gym & TF-Agents
27. 27Section 25: Deploying and Scaling TensorFlow Models in Production
28. 28Final Exam

Course facts

At a glance

Course

Applied Machine Learning (CS 460)

Course code

CS 460

Track

AI & data

Price

$50 $104.99

Lessons

179

Total runtime

19:36:49

Delivery

100% online, self-paced

Language

English

On completion

Certificate of completion — a non-degree credential