Embeddings are at the heart of machine learning. Embeddings allow us to represent any imaginable object as a list of numbers which can be processed by models. This idea is shockingly powerful. Literally anything, a picture of a car, a poem you wrote in fifth grade, the sound of your favourite song or something as abstract as a stream of vibrations in the Earth’s crust. By formulating all these different inputs into a consistent form we can leverage similar techniques to do useful work such as description, prediction and prescription.

Vectors are at the heart of modern machine learning techniques. LLMs are powered by the transformer which operates on language tokens which are mapped to embeddings that have around 1000 dimensions. Similarly, vision models represent images as pixels of colour which are translated to vectors (or tensors), audio models represent sound as frequencies and amplitudes which are again translated to vectors. Vectors are a core computational input and processing component throughout machine learning.

LLMs have grown from 200M parameters up to the estimated 6T parameter models we see today - a factor of 10,000 - let’s explore what innovations made that possible by stepping through the largest models at the time and their specific innovations.

Optimisation is at the core of AI research. We spawn instances of massive models with trillions of parameters and then try to optimise their parameters towards some goal, typically represented by a loss function. We’ve become really good at this type of optimisation because it has a key property: we can calculate the gradient. Packages such as PyTorch automatically calculate the expected changes in our loss function if we were to tweak parameters (the gradients) which allows us to make meaningful progress towards the goal. But what if you don’t have gradients?

The traditional AI agents that we see in the news, such as AlphaGo, Pokerbot were trained in well-scoped environments, but as we look to the future, we want AI that are capable of working towards more complex tasks in richer environments. We’ve seen some really amazing environments and agents pop-up recently, so let’s explore them! Across these environments, agents have been programmed to acquire knowledge, have complex social interactions, learn how to interact with the physical world and been thrown in the deep-end with virtually unlimited access to the world’s resources.

Self-supervised learning is a popular method for training models across many fields of AI. It represents a paradigm that does away with one of the toughest challenges of machine learning applications - labelling a dataset. Self-supervised learning leverages massive unlabelled databases by creating its own labels to learn useful representations of data which can later be used for downstream tasks, often leveraging some unrelated training objective. In this article, we’ll discuss the key self-supervised learning methods and how they relate to each other.