Resources

Jump to: Software • Prereq Resources

Software

For this course, we strongly recommend using a custom environment of Python packages all installed and maintained via the free [conda package and environment manager] from Anaconda, Inc.

For detailed instructions, see the [Python Setup page]

Past Offerings of COMP 135 at Tufts

• 2018 fall, with Prof. Liping Liu
• 2018 spring, with Prof. Liping Liu
• 2017 fall, with Prof. Roni Khardon (sorry, website no longer available)
• 2016 spring, with Kyle Harrington

Prereq Catchup Resources

Here are some useful resources to help you catch up if you are missing some of the pre-requisite knowledge. Please contribute new resources by starting a topic on the discussion forum.

To achieve this objective, we expect students to be familiar with:

Probability

• Key concepts:
• • Definition of a probability density function
• • Definition of a cumulative density function
• • Expecations of random variables
• • Gaussian distributions (univariate and multivariate)
• • Bayes theorem and associated algebra

• Possible resources:

• • David Mackay's "The Humble Gaussian Distribution" tutorial: http://www.inference.org.uk/mackay/humble.pdf
• • Stanford CS229 notes on Gaussian distributions: http://cs229.stanford.edu/section/gaussians.pdf

Linear algebra

• Key concepts:
• • matrix multiplication
• • matrix inversion
• • 'least-squares' closed-form solution to linear regression
• Possible resources:
• • Immersive Linear Algebra: http://immersivemath.com/ila/
• • Essence of Linear Algebra videos: https://www.youtube.com/playlist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab
• • 'Computational Linear Algebra for Coders' course by fast.ai: https://github.com/fastai/numerical-linear-algebra/blob/master/README.md
• • Goodfellow et al's chapter on Linear Algebra: http://www.deeplearningbook.org/contents/linear_algebra.html

First-order gradient-based optimization

• Key concepts:
• • Gradient descent
• • Learning rates
• • Difference between convex and non-convex functions for minimization
• Possible resources:
• • Convex Optimization overview for Stanford CS229: http://cs229.stanford.edu/section/cs229-cvxopt.pdf
• • Jupyter notebook on 'Linear Regression with NumPy' (fits linear model with gradient descent): https://www.cs.toronto.edu/~frossard/post/linear_regression/