Deep Learning in R

Term: 
Spring
Credits: 
1.0
Course Description: 

Machine learning has made significant progress in the last decade. The cutting edge in machine learning could not even come close to approximating human performance in image recognition, natural language processing, or many other tasks as recently as five years ago. However, the advent of deep learning has closed this gap, and even overtaken the limits of human performance. Deep learning may be the single most overhyped technology of the decade, however there’s no denying that the techniques it introduces and the capabilities it unleashes have already revolutionized the world. At the core of many of these advances, is Google’s open source package Tensorflow. In this course we will use the R keras package. This package provides an interface into Keras, allowing the user to build models, explore them, and to operationalize them inside of the familiar R programming language.

Learning Outcomes: 

By successfully completing the course the students will be able to:
● Explain deep learning from first principles
● Setting up their own deep-learning environment
● Build Image classification and generation models
● Apply deep learning for text and sequences

These topics can easily fill an entire PhD’s worth of coursework, so this course will provide an overview and example code and use-cases for the standard applications of deep learning.

Assessment: 

2 Daily Quizzes (30%)
End of Course Assignment (60%)
Intellectual Presence (10%)

Note on Intellectual Presence
To be counted as intellectually present, you must demonstrate an intellectual presence, which means you are engaged in all classroom activities. An intellectual absence (including reading non-course related material, playing/texting on phone, using a laptop for non-class related activities) will be counted as an absence. Students who anticipate the need to be absent should be aware that this course is very compressed, and any absence will make it very challenging to complete this course.

Prerequisites: 

Data Science and Machine Learning 1.: Concepts, Data Science and Machine Learning 2.: Tools, Data Science on Unstructured Text Data

File Attachments: