PinnedHow to find Sentence Similarity using Transformer Embeddings : BERT vs SBERTA computer program can pretend to take text and images as input, and give text and images as output, but on the inside it is just a number crunching machine. All that a computer understands is numbers, and all that it can do is arithmetic : addition, subtraction, multiplication and…Large Language Models5 min readLarge Language Models5 min read
Jul 28Sanskrit NLP : Classification of Bhagavad Gita vs Yoga SutrasWork done by Srihari K. G. during summer 2023 and mentored by Kushal Shah. Bhagavad Gita and the Yoga Sutras are two ancient Sanskrit texts containing a lot of spiritual wisdom that has transformed many lives over the centuries. Although these texts have been analyzed by many scholars from a…Naturallanguageprocessing12 min readNaturallanguageprocessing12 min read
Jul 19Is chatGPT good at logical thinking?This is perhaps the most important question on people’s mind since chatGPT was released in November 2022, and has serious implications for life and work in the AI era. There have also been some studies done to analyse the logical thinking abilities of chatGPT and other such AI tools. The…ChatGPT3 min readChatGPT3 min read
Apr 30Python Programming Practice ProblemsHere is a list of problems with gradually increasing difficulty levels that can help students in learning Python programming in a systematic way. The problems are chosen such that they are related to basic math so that there can be a better appreciation for the task and the solution. Concept…Python4 min readPython4 min read
Apr 5How does GPT do in-context learning?A reader of my blog on Pre-training, fine-tuning and in-context learning in Large Language Models (LLMs) asked “How is in-context learning performed?” and frankly speaking, this seemingly simple question is actually very complicated! So I decided to have a conversation with the GPT-powered Bing chat to see if it can…Large Language Models6 min readLarge Language Models6 min read
Jan 24Statistics, Machine Learning and Artificial IntelligenceLet’s start with a fact. Many companies that claim to be AI based actually don’t use any AI. They don’t even need AI! Does it really matter? Not much for the customers since they don’t pay unless the product has sufficiently high utility for them, irrespective of whether it has…4 min read4 min read
Jan 21Curated Machine Learning Datasets for College StudentsThere are a lot of Machine Learning datasets available on the internet, but not every dataset would be of interest to a college student who has started learning Machine Learning. In this blog, we share links to 10 interesting datasets for Machine Learning practice that we have handpicked for college students. Hope you find this useful! International football results from 1872 to 2022 https://www.kaggle.com/datasets/martj42/international-football-results-from-1872-to-2017Machine Laerning1 min readMachine Laerning1 min read
Aug 19, 2022NLP90 : Self-learn NLP in 90 hoursPre-requisites : Basics of Machine Learning The content is designed so that you spend 6hrs per week for around 15 weeks making it 90 hrs (assuming good familiarity with general ML algorithms and Python). Of course, you are free to speed up or take it easy! Week 1 : General Reading https://towardsdatascience.com/your-guide-to-natural-language-processing-nlp-48ea2511f6e1 https://medium.com/@ageitgey/natural-language-processing-is-fun-9a0bff37854eMachine Learning3 min readMachine Learning3 min read
Aug 6, 2022Pre-training, fine-tuning and in-context learning in Large Language Models (LLMs)Since the advent of Transformers in 2017, Large Language Models (LLMs) have completely changed the process of training ML models for language tasks. Earlier, for a given task and a given dataset, we used to play around with various models like RNNs, LSTMs, Decision Trees, etc by training each of…Machine Learning6 min readMachine Learning6 min read
Mar 26, 2022Fictometer : A simple and explainable algorithm for sentiment analysisOur ability to solve NLP problems using AI algorithms has advanced a lot, but our understanding of human language is yet to catch up. This is because most of the AI algorithms operate like a blackbox and even though we know the model architecture and all the parameter values, figuring…Naturallanguageprocessing3 min readNaturallanguageprocessing3 min read
