How to Build a Transformer from Scratch
An explanation of the Transformer architecture used in LLMs and a breakdown of the blocks involved in an encoder-only transformer.
Software Engineer @ PortSwigger
An explanation of the Transformer architecture used in LLMs and a breakdown of the blocks involved in an encoder-only transformer.
A step-by-step explanation of how autoencoders compress and reconstruct images using neural networks.
A breakdown of how convolutional neural networks process images, covering convolution, max pooling, and backpropagation.
An introduction to how neural networks learn, covering multilayer perceptrons, gradient descent, and backpropagation.
An explanation of how the perceptron classifies linearly separable data using gradient descent.