PinnedPinaki BrahmaBecoming the Ultimate RAG Picker for Your LLMThere are a lot of articles that talk about RAGs and some ‘hello world’ use cases where they implement RAGs along with LLMs to generate…May 20May 20
PinnedPinaki BrahmaUnraveling the `testing` hurdle in data science solutionsI am a data scientist, like many of you, who have struggled to write ‘tests’. Not anymore though — thanks to an almost five-year-old video…May 11May 11
Pinaki BrahmaLearn about Consensus clustering — an ensemble for unsupervised learningIt is common practice to use a set of week supervised learning algorithms to build a powerful ensemble model. However, the same principle…Sep 4Sep 4
Pinaki BrahmaLearn about the most popular unsupervised learning approach — clustering algorithmsThere is more to clustering algorithms than just the K Means. Let’s learn together some of the most popular ones today.Aug 31Aug 31
Pinaki BrahmaIntroduction to Graphs in Machine Learning — Part 1This single blog will help you understand the core terminologies in Graph Theory and relate them to how we solve ML related problems.Aug 19Aug 19
Pinaki BrahmaA vector store indexing (& search) with HNSWHierarchically Navigable Small World! A scalable approach to search millions of data points and get the most similar one. What is a Small…Aug 15Aug 15
Pinaki BrahmaWhy do we need a (Q)LoRA for finetuning LLMsCan you use LLMs to accurately answer questions specific to your industry? The answer most likely is a ‘No’. This article will help you…Aug 4Aug 4
Pinaki BrahmaEvolution of Optimizers in Deep Learning NetworksThis article will walk you through the journey from GD to Adam, and what is there beyond.Aug 4Aug 4
Pinaki BrahmaA primer in Activation FunctionsActivation functions are an integral part of any neural network. Without these, a neural network would just be a very bulky linear model.Jul 21Jul 21
Pinaki BrahmaA ‘run down’ on Gradient DescentIntuition, Mathematics and Code for Gradient Descent. You know this well, and you are ready for anything the ML world throws at you. Well…Jun 21Jun 21