CS480/680 Fall 2020 - Introduction to Machine Learning

GPU and TPU Acceleration

For GPU and TPU acceleration, feel free to use Google's Colaboratory environment. This is a free cloud service where you can run Python code (including TensorFlow and PyTorch, which are pre-installed) with GPU or TPU acceleration. A virtual machine with two CPUs and one GPU or TPU will run up to 12 hours after which it must be restarted. The following steps are recommended:

• Create a Python notebook in Google Colab
• Click on "edit", then "notebook settings" and select "None" (CPU), "GPU" or "TPU" for hardware acceleration.

Textbooks

There are many good references for machine learning. We will cover material in different textbooks. The first six textbooks are freely available online. Complementary readings in the textbooks are assigned for every lecture in the course schedule.

• [GBC] Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning (2016) freely available online
• [HTF] Trevor Hastie, Robert Tibshirani and Jerome Friedman, Elements of Statistical Learning (2nd edition, 2009) freely available online
• [D] Hal Daume III, A Course in Machine Learning (2017) freely available online
• [B] Christopher Bishop, Pattern Recognition and Machine Learning (2006) freely available online
• [MRT] Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar, Foundations of Machine Learning (2012) freely available online
• [SSBD] Shai Shalev-Shwartz, Shai Ben-David, Understanding Machine Learning: From Theory to Algorithms (2014) freely available online
• [RN] Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (3rd Edition) (2010)
• [M] Kevin Murphy, Machine Learning: A Probabilistic Perspective (2012)