You are no doubt familiar with the Iris dataset: a dataset containing flower pedal shapes and their corresponding sub-type of Iris flower: Setosa, Versicolour, and Virginica.

We are going to take those pedal measurements, and predict the type of Iris we are looking at!

Let’s get the Iris dataset first. Turns out, Scikit Learn (your old friend from last semester) ships a copy of the Iris dataset with itself. So, we will load the dataset from it.

Hello everyone! It’s April, which means we are ready again for a new unit. Let’s dive in.

You know what’s better than one neural network? TWO!!! Multi-modal approaches—making two neural networks interact for a certain result—dominate many of the current edge of neural network research. In this unit, we are going to introduce one such approach, Generative Adversarial Networks (GAN), but leave you with some food for thought for other possibilities for what training multiple networks together can do.

Woof. As I begin to write this I should add that this unit is going to be conceptually dense. Though we are teaching one particular algorithm (incidentally, named, REINFORCE), the world of reinforcement learning is build by one, if not many, very advanced treatments in maths.

So if anything, I would focus on getting the conceptual flavor of how these problems are formulated and discuses. If you can be along for the mathematical and algorithmic journey, then even better — but by no means required or expected… There’s still lots for all of us to learn together.

Welcome back! I think, over the last few days, we have been hyping up convolutional neural networks enough such that you are probably ready to dive right in. So… Let’s, uh, motivate it first!

Why do we use a CNN?

Let’s think of a toy problem to play with. Given a pattern made using two colours (let’s name them a and b, or perhaps black and white), let’s classify whether it is the “zebra” pattern" or the “checkerboard” pattern.

Hello y’all! This quick post about… writing your first “article” (ahem, MA) for this class. To me, the most rewarding part of our journey together is to be able to support everyone through writing very presentable reports—even if it is on old or simple problems—but in the format from which you can easily jump off and write a fully-blown scientific article in the future.

exemplar we discussed

(Kameswari, Sravani, and Mamidi 2020)