Don’t Waste Time on Deep Learning Models

When building a Machine Learning solution, live by this rule: Data quality is more important than model complexity/fanciness As an AI practitioner, it’s important you shy away from model-centric Machine Learning, and embrace a data-centric approach. Often, implementing the latest model boosts accuracy by a few decimals at best, over a good baseline. Compared to model enhancement, ensuring you have high quality data can have 10x improvement. ============================= Interested in hiring me as a consultant? Join The Sound Of AI Slack community: Connect with Valerio on Linkedin: Follow Valerio on Facebook: Follow Valerio on Twitter: ​