InCodeXbyPraveen·Jul 7Online Softmax in AttentionA plain walk through the trick that lets attention compute softmax and the value multiply in a single streaming pass.
Praveen·Apr 8Convolutional kernelsIn this blog, I will go though convolutional kernel operation. I will talk about how kernels look like and how they are multiplied with…
Praveen·Apr 7Why Attention Models Take Longer to TrainTraining a vision transformer from scratch is a notoriously painful experience. Where a well designed CNN might converge in 30 to 50 epochs…
Praveen·Jun 26, 2025Goggle Gemma LLM Deployment on AWSA quick, hands-on guide to spinning up your own mini LLM demo for about the price of a coffee.
Praveen·Aug 20, 2024Understanding the Bias-Variance Tradeoff in Machine Learning“Kaamyaab hone ke liye nahin, Kaabil hone ke liye padho! (Study not to be successful, but to be capable!)” by Ranchoddas Shamaldas…
InCodeXbyPraveen·Aug 20, 2024Types of Loss functions and their use cases and codeIn the fields of machine learning and statistics, loss functions (also known as cost functions or objective functions) play a pivotal role…
Praveen·Aug 18, 2024Decoding the Transformer Model: Architecture, Loss Function, and Inference from the ‘Attention is…The “Attention is All You Need” paper by Vaswani et al. revolutionized the field of natural language processing (NLP) and machine learning…
Praveen·Jul 31, 2022ByteTrack …Because deep learning is not the ‘only’ solutionSeveral deep learning models(GoogleNet, Alexnet) exist that can perform object classification tasks quite efficiently. It is a simple task…
Praveen·Feb 17, 2022Double DQN on TurtleBot 2(ROS)Double DQN on TurtleBot 2(ROS)A response icon1A response icon1
InCodeXbyPraveen·Dec 23, 2021Generative Facial Prior GAN(GFP-GAN) ExplainedGFP-GAN generates high-resolution images by removing noise and degradation in the input image. Here I have explained the key architectural…