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.
- But what is a Neural Network? | Deep learning, chapter 1, 19 min
- Gradient descent, how neural networks learn | Deep learning, chapter 2, 21 min
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!