Current Status
Not Enrolled
Get Started
This course is currently closed
Neural networks and deep learning are state-of-the-art methods used to build powerful predictive systems and find latent patterns in large amounts of data. By the end of this course, you will be able to discuss these complex topics and build neural networks that solve real-world problems.

Click on the buttons below for more information about the course or proceed to Lesson 1 in the Course Content section to begin learning.

Data Society has designed the Introduction to Neural Networks & Deep Learning course for students who possess a strong foundation in Python and the common libraries: SciKit-Learn, Pandas, NumPy, and Matplotlib, as well as a foundational knowledge of statistics, unsupervised machine learning algorithms, and classification algorithms.

By the end of the course, students should be able to:

  • Define powerful applications and use cases that incorporate deep learning
  • Build foundational neural network models
  • Implement best practices on deep learning models

It is being delivered using a flipped classroom model that begins with self-paced instruction in the online learning portal and culminates with a 4-hour, online, instructor-led session.

Self-paced instruction

In the online learning portal, you will have access to video presentations of conceptual topics, knowledge checks, recorded coding walkthroughs, independent coding exercises, and links to additional resources. These materials are split into three lessons, as described below:

  • Lesson 1: This lesson has six topics that will introduce you to neural networks and have you quickly coding your own simple network with TensorFlow and Keras.
  • Lesson 2: This lesson dives deeper into neural networks. Its seven topics cover concepts such as backpropagation, gradient descent, activation functions, and more. You’ll also practice implementing custom neural network architecture using a robust dataset.
  • Lesson 3: This lesson has seven topics that will walk you through best practices for building a neural network model. We’ll discuss them in areas such as data preparation, model performance metrics, and tuning your neural network.

We suggest that you complete the topics in a linear fashion, and you are always welcome to repeat a topic that requires a little more review or practice.

Instructor-led Session

You will be assigned to one of two instructor-led sessions, based on your preferences and space available. These sessions are scheduled for December 7 from 8:30am – 12:30pm and December 8 from 1:00pm – 5:00pm. No matter which session you attend, you will have the opportunity to ask the instructors any outstanding questions from your online learning. You will also have the opportunity to apply the concepts you have learned to your own dataset with the benefit of an instructor’s and classmates’ insights.

This session will be conducted using the Zoom platform. Check your email for additional details and a meeting invite the week before the session!

  • Jon-Cody Sokoll

    Jon-Cody Sokoll will present the material for the self-paced portion of the course. He is a data scientist, machine learning consultant and educator based in Memphis, TN. His background in management consulting and social science research informs a practical approach to problem solving. Jon-Cody dedicates his time to closing the gap between machine learning research and its real-world applications. He provides machine learning and statistical programming classes for aspiring thru experienced data scientists.

  • Max Feinberg

    Max Feinberg will be running the instructor-led session in December. He is a machine learning and robotics consultant who is passionate about leveraging data to make informed decisions and to help improve how all manners of systems operate. He has a wide range of interests and has worked on projects related to medical devices, blood clots, insurance, hair care, and robots for the space station. With experience from working with Fortune 100 clients and NASA, Max is excited to shape the future of data science with Data Society.

  • Data Society

    Data scientists and instructional designers from Data Society work behind the scenes to curate material and design the course experience. Data Society’s mission is to integrate Big Data and machine learning best practices across entire teams and empower professionals to identify new insights. We provide high-quality data science training programs, customized executive workshops, and custom software solutions and consulting services. Since 2014, we’ve worked with thousands of professionals to make their data work for them

Have a question?

You may find the answers to your question in the course FAQ.

If your question is more specific in nature, we recommend that you post it in the course forum for the benefit of all students, or ask it during the instructor-led session.

You may also email for additional support.