2020 Machine Learning Curriculum

Virtual Machine Learning Boot Camp – August 6-7, 2020
(Thursday – Friday |  8:30 a.m. – 4:30 p.m.)

Daily Schedule
8:30am – Start of Instruction
10:00 a.m. – 10:30 a.m. Break
12:00 p.m. – 1:00 p.m. Lunch
2:30-3:00 p.m. – Break
4:30 p.m. End of Instruction

This two-day boot camp will provide a broad introduction to Machine Learning (ML) from an executive perspective. Our goal is to give a manager or a CEO in a field such as medicine, finance, manufacturing, or energy an introduction to the essential concepts behind Machine Learning. Taught by a team of Rice professors in the computational sciences, the Machine Learning Boot Camp will integrate lectures describing the basic concepts to state-of-the-art Machine Learning. 

The boot camp assumes no specific prerequisites and will highlight a broad set of concepts, ranging from classical supervised (e.g., linear regression, logistic regression and decision trees) and unsupervised methods (e.g., clustering algorithms, principal components analysis) to modern machine learning approaches (e.g., different neural network architectures, min-max games and generative models, deep reinforcement learning), with numerous case studies and applications. Throughout its duration, the workshop will provide practical suggestions to executives with DOs and DON’Ts when using Machine Learning in practice. 

By the end of the boot camp, participants will be familiar with the following topics:

  • What is ML? What is it good for?
  • Fundamentals of ML (training/testing/validation, loss functions, featurization, regularization), along with the basics of optimization.
  • ML models: linear regression, logistic regression, kernel methods, support vector machines, clustering methods, dimensionality reduction techniques.
  • Decision trees, random forests, ensemble methods, boosting and bagging.
  • Fundamentals of Deep Learning: basic feedforward neural networks and the perceptron, optimization methods in neural networks and backpropagation, convolutional neural networks, autoencoders and variational autoencoders, recurrent neural networks and LSTMs, generative models and GANS.
  • Reinforcement learning and its applications in deep learning.

Participants at all career stages are welcome to attend. Note that the boot camp is meant as an executive-level summary of ML; hands-on ML programming is not part of the curriculum. We plan to offer an engineering-focused ML Boot Camp at a later time.

Curriculum

Thursday, August 6, 2020

AM Session: Fundamentals of ML

  • What is ML?
  • History of ML–1950’s through present day
  • ML success stories
  • ML failures
  • Types of learning
  • Learning loss
  • Features, parameters, and fitting
  • Training, testing and validation

PM Session: Basic Methods

  • Linear and logistic regression
  • SVMs and kernels
  • Decision trees, random forests, ensemble methods (boosting and bagging)
  • Regularization
  • Clustering and dimensionality reduction

Friday, August 7, 2020

AM Session: Deep Learning

  • The basics of neural networks: Multi-layer perceptron
  • Backpropagation and stochastic gradient descent
  • Convolutional and recurrent neural networks

PM Session: Advanced Deep Learning and RL

  • Autoencoders and variational autoencoders
  • Generative adversarial networks
  • (Deep) reinforcement learning
  • Overview of modern ML tools: TensorFlow and PyTorch

Prerequisites: A general level of familiarity with mathematics is assumed, including college-level calculus, though those without this background will still find the boot camp a useful introduction to modern ML.

Comments are closed.