LLM evaluation metrics — BLEU, ROGUE and METEOR explainedThese metrics are typically used to compare the similarity between 2 texts. In the context of LLMs, this would typically be comparing the…Aug 7Aug 7
Building a Binary Search Tree from scratchImplementation of Binary Search Tree in python with heuristic explanations for each stepFeb 171Feb 171
Segment Anything Model (SAM) by Meta — ExplainedA first attempt at a foundation model for computer visionApr 7, 20231Apr 7, 20231
LLMs for dummies — Understanding Large Language Models GPT, BERT, T5LLMs, true to their name, are large models trained on huge text corpus in a self supervised manner so that it develops a general…Feb 7, 2023Feb 7, 2023
Writing a custom operator in TFLite — GPUPorting your model with a custom operator to TFLite and running it on your mobile gpu just got easier.May 8, 2022May 8, 2022
Intuition for concepts in TransformersRead this before reading “attention is all you need” paperOct 18, 2021Oct 18, 2021
Published inThe StartupEfficientNet and EfficientDet ExplainedEfficientDet and EfficientNet are the latest object detection models from Google, that can scale depending on the use case.Nov 23, 2020Nov 23, 2020
Wtf is a ROC curve and how to use it?Understanding ROC and AUC for binary classification modelsAug 3, 20201Aug 3, 20201
Automatic Differentiation ExplainedHow Deep Learning libraries handle gradientsMay 9, 2020May 9, 2020
Published inMac O’ClockGrand Central Dispatch: Threads vs Queues, Sync vs Async, Serial vs ConcurrentUnderstanding GCD’s difficult jargonApr 4, 2020Apr 4, 2020
