Reinforcement Learning Bundle

177 Enrolled
4 Courses & 19.5 Hours
$39.00$660.00
You save 94% -

What's Included

Bayesian Machine Learning in Python: A/B Testing
  • Certification included
  • Experience level required: All levels
  • Access 40 lectures & 3.5 hours of content 24/7
  • Length of time users can access this course: Lifetime

Course Curriculum

40 Lessons (3.5h)

  • Introduction and Outline
    What's this course all about?2:18
    Where to get the code for this course1:17
    How to succeed in this course3:26
  • Bayes Rule and Probability Review
    Bayes Rule Review9:28
    Simple Probability Problem2:03
    The Monty Hall Problem3:57
    Imbalanced Classes4:40
    Maximum Likelihood - Mean of a Gaussian4:52
    Maximum Likelihood - Click-Through Rate4:23
    Confidence Intervals10:17
    What is the Bayesian Paradigm?5:46
  • Traditional A/B Testing
    A/B Testing Problem Setup4:26
    Simple A/B Testing Recipe5:07
    P-Values3:53
    Test Characteristics, Assumptions, and Modifications6:45
    t-test in Code3:23
    0.01 vs 0.011 - Why should we care?1:46
    A/B Test for Click-Through Rates (Chi-Square Test)6:04
    CTR A/B Test in Code8:50
    A/B/C/D/… Testing - The Bonferroni Correction2:20
    Statistical Power3:08
    A/B Testing Pitfalls4:01
    Traditional A/B Testing Summary3:42
  • Bayesian A/B Testing
    Explore vs. Exploit4:00
    The Epsilon-Greedy Solution2:58
    UCB14:35
    Conjugate Priors7:04
    Bayesian A/B Testing4:10
    Bayesian A/B Testing in Code8:50
    The Online Nature of Bayesian A/B Testing2:31
    Finding a Threshold Without P-Values4:52
    Thompson Sampling Convergence Demo4:01
    Confidence Interval Approximation vs. Beta Posterior5:41
  • Practice Makes Perfect
    Exercise: Compare different strategies2:06
    Exercise: Die Roll2:38
    Exercise: Multivariate Gaussian Likelihood5:41
  • Appendix
    How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow17:32
    How to Code by Yourself (part 1)15:54
    How to Code by Yourself (part 2)9:23
    Where to get Udemy coupons and FREE deep learning material2:20

Bayesian Machine Learning in Python: A/B Testing

LP
Lazy Programmer

The Lazy Programmer is a data scientist, big data engineer, and full stack software engineer. For his master's thesis he worked on brain-computer interfaces using machine learning. These assist non-verbal and non-mobile persons to communicate with their family and caregivers.

He has worked in online advertising and digital media as both a data scientist and big data engineer, and built various high-throughput web services around said data. He has created new big data pipelines using Hadoop/Pig/MapReduce, and created machine learning models to predict click-through rate, news feed recommender systems using linear regression, Bayesian Bandits, and collaborative filtering and validated the results using A/B testing.

He has taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Humber College, and The New School.

Multiple businesses have benefitted from his web programming expertise. He does all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies he has used are: Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases he has used MySQL, Postgres, Redis, MongoDB, and more.

Description

A/B testing is used everywhere, from marketing, retail, news feeds, online advertising, and much more. If you're a data scientist, and you want to tell the rest of the company, "logo A is better than logo B," you're going to need numbers and stats to prove it. That's where A/B testing comes in. In this course, you'll do traditional A/B testing in order to appreciate its complexity as you elevate towards the Bayesian machine learning way of doing things.

  • Access 40 lectures & 3.5 hours of content 24/7
  • Improve on traditional A/B testing w/ adaptive methods
  • Learn about epsilon-greedy algorithm & improve upon it w/ a similar algorithm called UCB1
  • Understand how to use a fully Bayesian approach to A/B testing

Specs

Details & Requirements

  • Length of time users can access this course: lifetime
  • Access options: web streaming, mobile streaming
  • Certification of completion not included
  • Redemption deadline: redeem your code within 30 days of purchase
  • Experience level required: all levels, but knowledge of calculus, probability, Python, Numpy, Scipy, and Matplotlib is expected
  • All code for this course is available for download here, in the directory ab_testing

Compatibility

  • Internet required

Terms

  • Unredeemed licenses can be returned for store credit within 30 days of purchase. Once your license is redeemed, all sales are final.