Interested in AI and Machine Learning?



Firstly, what is the difference between AI and ML? Here’s a helpful analogy: You can think of deep learning, machine learning and artificial intelligence as a set of Russian dolls nested within each other, beginning with the smallest and working out. Deep learning is a subset of machine learning, and machine learning is a subset of AI, which is an umbrella term for any computer program that does something smart. source

A couple of useful videos to get you started.

I’d also recommend the Skymind artificial intelligence wiki as a good starting point for reading about the various topics of AI.

Looking for a Python library to get yourself started? After some quick research, the two you are most likely going to hear about are Pytorch and Tensorflow. Based on the following, it looks like PyTorch would be the better option for student programmers: PyTorch is better for rapid prototyping in research, for hobbyists and for small scale projects. TensorFlow is better for large-scale deployments, especially when cross-platform and embedded deployment is a consideration. source

Alternatively, you could go down the path that Peter in Y11 took for his Personal Project and code it yourself without a library. There are some good resources available for that as well.

Look into terms such as deep reinforcement learning if your interest is in writing an AI agent to play a computer game. Where as convolutional neural networks is the branch of AI for things like image processing and recognition.

Either way, be prepared that to venture down the rabbit hole of ML is to be prepared for teaching yourself some new math along the way. Vectors, matrices, statistics and even some calculus are key to understanding the concepts of ML.

What questions do you have about AI or ML? Share any useful resources you come across!


I can certainly recommend “The Coding Train” (Youtube) for useful information involving ML, especially if you’re interested in programming something from scratch.


Yeah I’ve used Daniel Shiffman’s resources in the past, they are always high quality - thanks for the reminder - he has added a ton of new videos since I last looked at his channel.

Taking a quick look through his playlists, his a beginner’s guide to machine learning with ml5.js series of 10 introductory vids look like a good place for someone to start who needs an overview of the concepts.

All up he has over 100 videos on machine learning here! Also he has an online book, the Nature of Code. The guy is a resource creating machine!

That intro playlist uses ml5.js which “aims to make machine learning approachable for a broad audience of artists, creative coders, and students. The library provides access to machine learning algorithms and models in the browser, building on top of TensorFlow.js”. It looks quite easy to get up and running with provided models. Obviously if you are only writing a a few lines of code, you aren’t doing much yourself, you’re just using the work others have done before you. But the lessons start simple and get more complex as they go.

@ChilledGumbo, any particular videos from Coding Train you’d recommend for someone wanting to build their own network?


Posting this here so they can be found again in the future. Some very useful datasets for anyone looking to get started with ML.

Collections of datasets you can use to train your own models:

Collections of pre-trained models that are ready to use:

By the way, if advances in AI and ML are your interest, I recommend checking/reading Google’s official AI blog from time to time.


A couple of CGP Grey videos that do a good job of explaining the basic ideas behind machine learning without getting into the technical or math.

And a bonus, is automation inevitable? Are we rapidly on the way to a world in which Humans need not apply. A fascinating discussion about the future of the human workforce in light of the growth of machine learning and robotics. As students preparing to enter this employment market, what are the jobs that will be irreplaceable?