Neural Networks and Deep Learning

Next Offering 

Start Date: August 24th, 2021
End Date:  October 12th, 2021

Neural Networks and Deep Learning is one of six non-credit courses in the Certification in Practice of Data Analytics (CPDA) program. This course can be taken individually or as one of four courses required to receive the CPDA certificate of completion.

Neural Networks and Deep Learning can be taken after Statistics in the CPDA program. It's recommended that students also complete Machine Learning first, but not required. After studying the construction of algorithms in Machine Learning, students take a deeper dive in the field of neural networks, a subset of Machine Learning.  

The course is taught by faculty from the College of Engineering at The Ohio State University. The course is delivered in 100% distance learning format and includes instructional material equivalent a one semester credit hour class.  

Course Description

Deep learning (DL) is an important subset of machine learning (ML) methods that is based on artificial neural networks (ANNs), which are biologically-inspired function representations that enable a computer to learn directly from observational data. In this course, students will learn the foundations of DL, the most powerful ANN architectures, practical and efficient methods for training large-scale and complex ANN structures, and about important applications of DL in a variety of fields such as computer vision, speech recognition, drug discovery, healthcare, chemical engineering, and many others. 

4 CEUs are granted upon successful completion of the course.
 

You Will Learn to:

1. Understand the key technology trends driving the field of deep learning
2. Be able to construct, train, and apply deep neural networks
3. Recognize important parameters in the architecture of a neural network
4. Apply regularization and cross-validation methods to avoid overfitting data
5. Identify which deep learning methods are best suited for a given task
6. Use Python and TensorFlow to build flexible and efficient deep/machine learning models

Prerequisites 

Familiarity with calculus, convex functions and sets, differentiation of multivariate functions, taylor series for multivariate functions, and basic probability and statistics (random variables, expectation, mean and covariance, characteristic functions, central limit theorem, etc.) Some basic experience with a high-level programming language such as Python, R, Matlab, or Julia.

This course can be taken individually, or as one of four courses required to receive the CPDA certificate of completion. It is required that participants will have taken Introductory Statistics for Data Analytics first. It is recommended that students take Machine Learning before this course as well but not required. 
          

Click Here to learn more about how this course is delivered 100% online!
 

Expected Time Commitment to Complete this Course

Each course is equivalent to a one semester credit hour class. Therefore each class consists of approximately 40 hours of class time that includes 12-13 hours of recorded faculty lectures and 23-24 hours of additional course work. Each course is seven weeks in length, so each week there is 5.7 hours of combined class time (40 hrs / 7 weeks). The average student should allow a 2:1 study-to-class-time ratio to complete the course. This means you should plan to study two hours for each one hour of class time. This equates to 11-12 hours each week to complete all course work. (5.7 hrs X 2 = 11-12 hrs).  Based on a person's own personal strengths and experience, you should increase or decrease the ratio. 
 

Cancellations and Refunds

A full refund minus a $75 administrative fee will be made if cancellation is received three weeks prior to the start of the course. No refunds within three weeks of the course start date. 

Course Offering Dates

Each course offering in this program is faculty lead and therefore operates with a specific start date and end date. Students must complete each course during the specific time frame. Access to the online course and materials is removed when the course ends.