The Creative Side of AI: Product Name Generation
summary
A name-generator built from language models and transformer components, trained on scraped Wikipedia and product review text using one-hot encoding and sequence windows to produce product names. It compares feed-forward, recurrent, and transformer model types, describes data preparation, simple postprocessing rules and failure modes, and shows an analytics platform that runs inference to return ranked candidate lists (with examples like “Power Auto”) plus deployment steps to make generated names usable.
AI-written summary · about
chapters (7)
- 0:00AI and product naming
- 3:40Language modeling for names
- 9:12Sequence limitations in networks
- 15:02Text to creative names
- 22:28Demo: analytics platform
- 29:27Creative name examples
- 33:13Q&A
related talks
49mUsing Generative AI to Strengthen & Accelerate Learning
22mGenerative AI - A Pragmatic Business View
18mBuilding an AI service without training – AI translations with LLMs
55mAI Showdown: The Good, The Glitchy, and The Risky
49mGenerative AI: Concepts, Tools, and Applications for Data Professionals
37mBest AI Tools for Web Developers / How to Use AI in Web Development
33mThe Dawn Of Universal Creativity
24mGenerative AI: Business or Feature?