Core: Spring 2020

You always start with the basics, and with AI it's no different! We'll be getting our feet wet with some simple, but powerful, models and demonstrate their power by applying them to real world data.

In this lecture, we explore powerful yet lightweight models that are often overlooked. We will see the power of combining multiple simple models together and how they can yield amazing results. You won't believe how easy it is to classify with just a line!

You've heard about them: Beating humans at all types of games, driving cars, and recommending your next Netflix series to watch, but what ARE neural networks? In this lecture, you'll actually learn step by step how neural networks function and learn. Then, you'll deploy one yourself!

Ever wonder how Facebook tells you which friends to tag in your photos, or how Siri can even understand your request? In this meeting we'll dive into convolutional neural networks and give you all the tools to build smart systems such as these. Join us in learning how we can grant our computers the gifts of hearing and sight!

This lecture is all about Recurrent Neural Networks. These are networks with memory, which means they can learn from sequential data such as speech, text, videos, and more. Different types of RNNs and strategies for building them will also be covered. The project will be building a LSTM-RNN to generate new original scripts for the TV series "The Simpsons". Come and find out if our networks can become better writers for the show!

It's time to put what you have learned into action. Here, we have prepared some datasets for you to build a a model to solve. This is different from past meetings, as it will be a full workshop. We provide the data sets and a notebook that gets you started, but it is up to you to build a model to solve the problem. So, what will you be doing? We have two datasets, one is using planetary data to predict if a planet is an exoplanet or not, so your model can help us find more Earth-like planets that could contain life! The second dataset will be used to build a model that mimics a pokedex! Well, not fully, but the goal is to predict the name of a pokemon and also predict its type (such as electric, fire, etc.) This will be extremely fun and give you a chance to apply what you have learned, with us here to help!

How can we infer on the past to predict the future? In this meeting we are going to be learning about time series data and its unique qualities. After we sharpen up our data science skills, we will be putting them to good use by analyzing and predicting the spread of the Coronavirus!

GANs are relativity new in the machine learning world, but they have proven to be a very powerful architecture. Recently, they made headlines in the DeepFake network, being able to mimic someone else in real time in both video and audio. There has also been cycleGAN, which takes one domain (horses) and makes it look like something similar (zebras). Come and learn the secret behind these type of networks, you will be surprised how intuitive it is! The lecture will cover the basics of GANs and different types, with the workshop covering how we can generate human faces, cats, dogs, and other cute creatures!

We all remember when DeepMind’s AlphaGo beat Lee Sedol, but what actually made the program powerful enough to outperform an international champion? In this lecture, we’ll dive into the mechanics of reinforcement learning and its applications.

We've learned about linear and statistical models as well as different training paradigms, but we've yet to think about how it all began. In Cognitive Computational Neuroscience, we look at AI and ML from the perspective of using them as tools to learn about human cognition, in the hopes of building better AI systems, but more importantly, in the hopes of better understanding ourselves.