Machine Learning for Engineering and science applications

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!

Grab it

Recent applications of machine learning have exploded due to cheaply available computational resources as well as wide availability of data. Machine Learning (ML) techniques provides a set of tools that can automatically detect patterns in data which can then be utilized for predictions and for developing models. Developments in ML algorithms and computational capabilities have now made it possible to scale engineering analysis, decision making and design rapidly. This, however, requires an engineer to understand the limits and applicability of the appropriate ML algorithms. This course aims to provide a broad overview of modern algorithms in ML, so that engineers may apply these judiciously. Towards this end, the course will focus on broad heuristics governing basic ML algorithms in the context of specific engineering applications. Students will also be trained to implement these methods utilizing open source packages such as TensorFlow.
INTENDED AUDIENCE: Postgraduate students in all engineering and science disciplines. Mature seniorundergraduate students may also attempt the course.PREREQUISITES:Familiarity with Multivariable Calculus, Linear Algebra, Probability, Statistics. Comfortable with programming in PythonINDUSTRY SUPPORT: Should be of interest to companies trying to employ engineers familiar with Machine Learning

Syllabus

COURSE LAYOUT

Week 1: Mathematical Basics 1 – Introduction to Machine Learning, Linear AlgebraWeek 2: Mathematical Basics 2 - ProbabilityWeek 3: Computational Basics – Numerical computation and optimization, Introduction to Machine learning packagesWeek 4: Linear and Logistic Regression – Bias/Variance Tradeoff, Regularization, Variants of Gradient Descent, MLE, MAP, ApplicationsWeek 5: Neural Networks – Multilayer Perceptron, Backpropagation, ApplicationsWeek 6: Convolutional Neural Networks 1 – CNN Operations, CNN architecturesWeek 7: Convolutional Neural Networks 2 – Training, Transfer Learning, ApplicationsWeek 8: Recurrent Neural Networks RNN, LSTM, GRU, ApplicationsWeek 9: Classical Techniques 1 – Bayesian Regression, Binary Trees, Random Forests, SVM, Naïve Bayes, ApplicationsWeek 10: Classical Techniques 2 – k-Means, kNN, GMM, Expectation Maximization, ApplicationsWeek 11: Advanced Techniques 1 – Structured Probabilistic Models, Monte Carlo MethodsWeek 12: Advanced Techniques 2 – Autoencoders, Generative Adversarial Network