The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I Audited LIME on 30 Inputs and Found It Fails on the Easiest Ones. This experiment clearly shows when to use LIME and when not. https://medium.com/@parshvijain1508/i-audited-lime-on-30-inputs-and-found-it-fails-on-the-easiest-ones-20f3bf370274?sharedUserId=parshvijain1508
Also published it as a package on PYPI today: https://pypi.org/project/lime-audit/
medium.com
I Audited LIME on 30 Inputs and Found It Fails on the Easiest Ones
LIME is one of the most cited explanation methods in machine learning. It tells you which words in a sentence influenced a classifier’s…
XAI Forensics: Explainable Sentiment Analysis Tool
Built a full-stack Explainable AI platform to explore how transformer models interpret and classify...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Same thing in engineering. Before I write a line of Core ML pipeline code I sketch the data flow on paper — where the tensor lives, where it gets copied, what actually runs on the ANE. The messy version catches the expensive mistakes while they're still free to fix. The keyboard is where you commit; paper is where you're still allowed to be wrong.
Is sketching part of your creative workflow or we've forgotten what it feels to be human?
Depending on the projec's scope, I normally like to explore my ideas on paper before I come up with the best solution.
And no, they're not perfect.
They are rough and messy, my goal is so...
Weldone!
Too many businesses try to build complex predictive AI models before their basic data pipelines are even functioning. You cannot skip the fundamentals.
The Data Hierarchy of Needs for scaling SMBs:
Level 1: Stable Collection (SQL) — Your database health and data pipelines. If your raw data is broken, everything built on top of it will fail.
Level 2: Data Governance (Python) — Enforcing uniform definitions, cleaning messy data, and ensuring total integrity.
Level 3: Automated BI (Power BI) — Moving away from manual spreadsheets to automated executive views and daily KPI tracking.
Level 4: Predictive Insights (AI / ML) — Churn models and forecasting. This only generates ROI if levels 1 through 3 are rock solid.
Stop wasting time on manual data entry and broken reports. If you are stuck at Level 1 or 2, I can help you scale up. Check out my Contra services to get your SQL pipelines automated and your Power BI dashboards built right the first time.
Amazing Information