Model Explainability: Making Sense of SHAP and LIME
Your model just denied someone a loan, flagged a tumour, or rejected a job application — and when the person asks …
Abhay
5 min read
Your model just denied someone a loan, flagged a tumour, or rejected a job application — and when the person asks …
Abhay
5 min read
Here is a fact that should not work but does: the way modern AI makes a photorealistic corgi-astronaut is by starting …
Abhay
4 min read
Imagine teaching someone chess by never explaining the rules of strategy — you just let them play a few million games …
Abhay
4 min read
If a regular chatbot is a clever intern who answers whatever you ask, an agentic system is the same intern after you …
Abhay
4 min read
Ask a large language model a question and it will answer with total confidence, whether or not it has any idea what …
Abhay
4 min read
Every machine learning project eventually hits the same wall: the model is hungry, and you are out of data. Labelling …
Abhay
4 min read
There is a specific flavour of dread reserved for the sentence “but it worked on my machine last Tuesday.” A …
Abhay
4 min read
Your classifier spits out a number between 0 and 1. To turn that into a yes/no answer, you pick a threshold — say, 0.5 — …
Abhay
4 min read
There’s a moment in every machine learning project where you stop modelling and start fiddling. Should it be a …
Abhay
4 min read