Explainability and Interpretability in AIWhen it comes to implementing any ML model, the most difficult question asked is how do you explain it. Suppose, you are a data scientist…Jan 26, 2023Jan 26, 2023
Diffusion Models in hi-fi Image SynthesisDiffusion model was developed by Ratcliff in the year 1978, and was used for reaction time analysis in the field of cognitive psychology…Mar 15, 2022Mar 15, 2022
How to be an efficient data scientistThis article definitely sounds like a cliché for someone who is striving to be a data scientist and have read numerous articles with the…Oct 11, 2021Oct 11, 2021
Performance measures in Forecasting, when to use whatFrom my experience, I have realized that the evaluation of a model requires more focus and effort than the model itself. The more complex…Aug 29, 2021Aug 29, 2021
Calibration in Neural NetsI remember an interview I gave few years back, where I was explaining a neural net classifier to the interviewer. He strongly believed only…May 30, 20211May 30, 20211
Word Embeddings, WordPiece and Language-Agnostic BERT (LaBSE)Word embeddings are the representation of words in a numeric format, which can be understood by a computer. Simplest example would be (Yes…Feb 20, 2021Feb 20, 2021
Graph Theory and Graph DatabaseIn “The Big Bang Theory” TV show S12:E16, Leonard created a whole network of celebrities who are likely to play Dungeons and Dragons with…Dec 20, 2020Dec 20, 2020
Latent Dirichlet Allocation (LDA) for Topic ModellingTopic modelling is a statistical technique used to extract specific topic is a given collection of documents. LDA is one of the most…Nov 30, 20201Nov 30, 20201
ELECTRA Vs BERT– A comparative studyWith the launch of ELECTRA, most likely we are set for another revolution in the NLP and NLU tasks and we are all looking forward to it…Nov 15, 2020Nov 15, 2020
A look into Regularized Greedy ForestAs the name suggests Regularized Greedy Forest is a forest, greedy and regularized :-). Let’s delve into more details.Nov 15, 2020Nov 15, 2020