This article demonstrates training a transformer model to run a multi-step algorithm in order to sort lists of numbers. My previous article demonstrated adding lists of numbers by showing the tran...

Following from my previous article I’ve trained a transformer model to perform symbolic addition. Given two numbers expressed as a sequence of digits, the model can output the sum of those numbers...

Transformer-based large language models have taken the world by storm in recent years, and achieved impressive capabilities in solving general reasoning problems.[3] That being said, LLMs are still...

Reinforcement learning is the subfield of machine learning that considers agents that learn behaviours through interaction with their environment. These systems have shown impressive capabilities ...

Recently I’ve been interested in using autoencoders to model environment dynamics in reinforcement learning tasks. As the agent interacts with the environment an autoencoder could be trained on th...

Convolutional autoencoders are a widely used network architecture for distilling the underlying structure of an input image into a smaller vector representation. One notable shortcoming of convolu...