Core Elements of Large Language Models (LLMs): Tokens, Context Windows, Temperature, and SamplingLearn the core elements of Large Language Models (LLMs), including tokens, context windows, temperature, Top-K, Top-P sampling, and repetition penalty6 min read·nishanthan.hashnode.devOct 26
How Query, Key, and Value (QKV) Work in TransformersEvery Transformer-based language model, from BERT to GPT, relies on a mechanism called attention to determine how different tokens in a sequence relate to one another. At the heart of this mechanism a7 min read·nishanthan.hashnode.devOct 22
Understanding Transformer: The Architecture Behind Modern AIWhat Is a Transformer? A Transformer is a neural network architecture introduced by Google researchers in 2017 in the paper Attention Is All You Need. It uses attention mechanisms to help the model le6 min read·nishanthan.hashnode.dev1Oct 15
Activation Functions in Neural Networks — A Practical Mental ModelIntroduction Activation functions decide how a neuron responds to an input signal. They introduce non-linearity, enabling neural networks to learn complex patterns. This article focuses on the most commonly used activation functions: Sigmoid Sof...4 min read·nishanthan.hashnode.devDec 22, 2025
Backpropagation in Deep Learning: A Complete, Intuitive, and Practical GuideIntroduction: Why Backpropagation Matters Backpropagation is the learning engine behind modern deep learning. Every time a neural network improves its predictions — from recognizing faces to generating text — the improvement comes from one mechanism:...6 min read·nishanthan.hashnode.devDec 17, 2025