upcarta
Sign In
Sign Up
Explore
Search
Faraz Munshi
Follow
1
Follower
community-curated profile
I share ideas on Machine Learning & Data Science | Masters in CS
Most Recommended
Most Recommended
Recent
Tweet
Tweet
Dec 12, 2022
A lot of time and effort is spent to improve accuracy of Machine Learning models. Despite achieving best performance with evaluation, models do fail in production. 90% of the time, it indicates a problem called Data Leakage. A thread.. Loooong ti
by
Faraz Munshi
Post
Add to Collection
Mark as Completed
Tweet
Feb 7, 2023
A poorly tuned model learns too slow, overfits/underfits or worsen accuracy. Hyper-parameter tuning by trial and error is impractical. Techniques of Grid and Random Search turn this tedious task into an automated task, saving your time and sanity.
by
Faraz Munshi
Post
Add to Collection
Mark as Completed
Tweet
Dec 19, 2022
Proper ML modeling starts with quality data.✅ Early on, you're going to have to tell between quality data and garbage.✅ Subject matter experts help make that distinction.✅ (Much before your feature engineering wizardry comes into play.) A note abo
by
Faraz Munshi
Post
Add to Collection
Mark as Completed
Tweet
Nov 25, 2022
Sudden dip in model performance! You're confused! Its your 'fav' colleague Karen, again! "Choice of algthm sucked from the start! "That series of costly label updates? What a waste!" She rubs it in. . . . . Wait, the last part rings a bell! Ohh..Kar
by
Faraz Munshi
Post
Add to Collection
Mark as Completed
