Learn about the basic principles and common terminology of neural networks.

In the past few years, use of artificial intelligence and machine learning techniques has been on the rise, and neural networks are at the heart of this movement. At times, the results produced by these networks seem mystical: how did your email platform correctly suggest the words you wanted to type? How does that photorealistic image depict a person who does not genuinely exist? How can a video clip so believably impersonate a person’s movements and voice?

As a tool, neural networks have a variety of uses; however, to determine whether they have applicability to a given context, we need to know what makes them tick–i.e., what inputs they require to generate meaningful outputs and what vocabulary is appropriate to use. 

This workshop aims to provide a beginner’s guide to neural networks, focusing more on concepts and terms than the underlying mathematics.

AFTER COMPLETING THIS WORKSHOP, PARTICIPANTS WILL BE ABLE TO:

• Articulate the basic idea of how neural networks operate. 
• Recognize the building blocks of a neural network.
• Name different types of neural networks, identifying each type by its specializations.
• Frame tasks in the form of a neural network through an understanding of potential input and output shapes.
• Reflect upon the applicability of neural networks to a given problem through a knowledge of neural network capabilities and limitations.

PREREQUISITES: 

• A facility with concepts of calculus (e.g., derivatives) and linear algebra (e.g., vectors and matrices) is useful, but it is not required–although neural networks are built on deep mathematical concepts, discussion of this material in the workshop will be light.
• No coding will be involved in this workshop.
• No laptops are required.