Home
SiliconSloth
Cancel

Learning Algorithms from Scratch

In the previous article we saw how a transformer model can learn to execute a multi-step algorithm to sort lists of numbers. One drawback of this approach is that we need to devise the algorithm o...

Learning Algorithms with a Transformer

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...

Adding Numbers with a Transformer

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...

Transformers as Rule Engines

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...

Thinking Ahead in Reinforcement Learning

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 ...

Autoencoders for Montezuma’s Revenge

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...

Autoencoders for Position Detection

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...