Data ScienceDiscover Coursera Plus
Data Science · Year 3 · Data, machine learning and AI
S6 Advanced AI
Master the three main pillars of modern AI: Bayesian inference, deep neural networks and reinforcement learning.
262hours of coursework
27weeks at 10 h
4steps
13new courses
4universities
Target skills
- Bayesian inference, MCMC, mixture models, time series
- Convolutional and recurrent networks, autoencoders, GANs
- Transfer learning and generative AI
- Markov decision processes, TD learning, Q-learning, policy gradient
Semester project
Two capstones: Bayesian Statistics (a complete Bayesian analysis of a dataset) and A Complete Reinforcement Learning System (an end-to-end agent).
Courses this semester
- 1University of California, Santa CruzIntermediateR, Microsoft Excel
Show the 5 courses
Course Level Length Rating (reviews) Bayesian Statistics: From Concept to Data Analysis Intermediate 11 h 4.6 (3,233) Bayesian Statistics: Techniques and Models Intermediate 30 h 4.8 (498) Bayesian Statistics: Mixture Models Intermediate 22 h 4.5 (63) Bayesian Statistics: Time Series Analysis Intermediate 19 h 4.3 (18) Bayesian Statistics: Capstone Project Advanced 12 h 4.5 (10) - 2Johns Hopkins UniversityIntermediatePython, TensorFlow, PyTorch
Show the 3 courses
Course Level Length Rating (reviews) Introduction to Neural Networks Intermediate 18 h 4.2 (10) Advanced Neural Network Techniques Intermediate 11 h — Practical Methodology and Ethics in AI Intermediate 7 h 4.5 (11) - 3Illinois TechIntermediateApache Hadoop, Apache Spark, NoSQL
Show the course
Course Level Length Rating (reviews) Deep Learning Beginner 57 h 4.5 (37) - 4University of Alberta (with Alberta Machine Intelligence Institute)IntermediatePython
Stated prerequisites: 1 year undergraduate CS or 2-3 years software development; Python; basic statistics, linear algebra and calculus
Show the 4 courses
Course Level Length Rating (reviews) Fundamentals of Reinforcement Learning Intermediate 15 h 4.8 (2,911) Sample-based Learning Methods Intermediate 22 h 4.8 (1,259) Prediction and Control with Function Approximation Intermediate 22 h 4.8 (851) A Complete Reinforcement Learning System (Capstone) Intermediate 16 h 4.7 (654)
Reading
Bayesian Data Analysis, 3rd ed.A. Gelman et al.The reference for applied Bayesian statistics; Parts I to III alongside UC Santa Cruz.Free PDF, non-commercial use
Deep Learning: Foundations and ConceptsC. M. Bishop, H. BishopRecent textbook (2024): from simple networks to transformers and diffusion models.Free online version
Deep LearningI. Goodfellow, Y. Bengio, A. CourvilleThe classic; Part I reviews the mathematics, Part II covers CNNs and RNNs.Free online
Reinforcement Learning: An Introduction, 2nd ed.R. S. Sutton, A. G. BartoThe official textbook of the Alberta specialization: chapters follow the order of the four courses.Free PDF
Things to watch
- Foundations of Neural Networks and the Illinois Tech Deep Learning course have few reviews (24 and 37); rely on Bishop or Goodfellow for theory.
- The Deep Learning course is taken on its own from Illinois Tech's Data Analytics and Deep Learning specialization.
With Coursera Plus
This semester takes 262 hours, about 6 months at 10 hours a week. A Coursera Plus subscription gives access to most of its courses during that time.