1. What is artificial intelligence
Artificial intelligence (AI) can be explained as machines behaving intelligently by problem solving or completing tasks. It is a very broad subject that involves computer science, cognitive science, mathematics, philosophy, neuroscience, linguistics and many other disciplines.
Check how much you know already about AI
Interested in learning about machine learning, artificial intelligence and deep learning? Check out these free resources online:
- fast.ai
- LinkedIn Learning (requires Charles Sturt University login)
- Coursera
Machine learning, neural networks, and deep learning
Machine learning
When most people mention AI, they’re usually talking about machine learning. This term covers algorithms that get better with experience, without needing specific instructions for every improvement. Examples of such algorithms include evolutionary algorithms, Markov chains, and neural networks.
Neural networks
Neural networks are algorithms, modelled after the human brain, that use a system of interconnected nodes called artificial neurons. This allows them to be trained, so that when given complex data, they can produce desired outputs. For example, let’s say we wanted a network that can recognise cats. We would give it two sets of images containing “cats” and “not cats”. Then neurons will apply mathematical operations to the image and produce a first guess. This guess is usually incorrect, however the network then adjusts these calculations until it responds to features of the training data (such as tails or whiskers) and starts being correct more often. Once training is complete, the network can be given new images. It will then use those features it learned during training to calculate the likelihood that any given image is a cat.
Deep learning
More complex problems require more artificial neurons. These neurons are usually arranged into “layers”. When there are many of these layers, it is referred to as a “deep” neural network. These are harder to train, requiring more data, but they can complete many more operations on inputs, making them better suited to complex tasks. This type of neural network is usually the kind you hear about playing board games, generating images or interpreting natural language.
But what *is* a Neural Network? | Deep learning, chapter 1 (YouTube, 18m40s) discusses the basics of what a neural network is and how deep learning occurs in machine learning.
