24 January 2019
3 Months, Online
6-8 hours per week
PRE-REQUISITES: The course requires an undergraduate knowledge of statistics, (descriptive statistics, regression, sampling distributions, hypothesis testing, interval estimation, etc.) calculus, linear algebra, and probability.
You should be comfortable with Python or any other programming language. All assignments/application projects will be done using the Python programming language using one or more of the following packages pandas, NumPy, Matplotlib, seaborn, scikit-learn, PyMC3 etc..
Machine Learning has become an entrenched part of everyday life. The books we buy, the movies we watch, the sports we follow, the driving directions we get are driven by Machine Learning algorithms. It is one of the most exciting fields of computing today. And Machine Learning practitioners are in high demand, with a shortfall of 250,000 data scientists forecast.
At Columbia Engineering, we are fascinated by the possibilities of Machine Learning. We have created the Applied Machine Learning course, in partnership with EMERITUS, to help students across the world apply Machine Learning to improve every aspect of human life.
Going beyond the theory, our approach invites participants into a conversation, where learning is facilitated by live subject matter experts and enriched by practitioners in the field of machine learning.DOWNLOAD BROCHURE
All assignments and application projects will be done using the Python programming language.DOWNLOAD SYLLABUS
You will build a movie recommendation engine by applying collaborative filtering and topic modelling techniques. You use a dataset which contains 20 million viewer ratings of 27,000 movies.
You will write code to predict house prices based on several parameters available in the Ames City dataset compiled by Dean De Cock using least squares linear regression and Bayesian linear regression.
You will predict the human activity (walking, sitting, standing) that corresponds to the accelerometer and gyroscope measurements by applying the nearest neighbours technique.
You will detect potential frauds using credit card transaction data. You will apply the random forest method to identify fraudulent transactions.
You will create market segments using the US Census dataset and by applying the k-means clustering method.
Note: All product and company names are trademarks™ or registered® trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.
John has a PhD from Duke and has been a postdoctoral researcher in the Computer Science departments at Princeton University and UC Berkeley. John Paisley’s research focuses on developing models for large-scale text and image processing applications. He is particularly interested in Bayesian models and posterior inference techniques that address the big data problem.
Carleton Smith is a Data Science educator and practitioner in Chicago, IL. Carleton has taught several data science courses at General...More info
Jacob is a mathematics educator, with a PhD in mathematics education from Columbia University. Currently, he teaches...More info
James H. Faghmous is a visiting assistant professor at Stanford University where he researches and mentors...More info
*Course Leaders are subject to change
Upon successful completion of the course, participants will receive a verified digital certificate from EMERITUS in collaboration with Columbia Engineering Executive Education.Get Certified