all AI news
Google's Image-Text AI LIMoE Outperforms CLIP on ImageNet Benchmark
July 19, 2022, 1 p.m. | Anthony Alford
InfoQ - AI, ML & Data Engineering www.infoq.com
Researchers at Google Brain recently trained Language-Image Mixture of Experts (LIMoE), a 5.6B parameter image-text AI model. In zero-shot learning experiments on ImageNet, LIMoE outperforms CLIP and performs comparably to state-of-the-art models while using fewer compute resources.
By Anthony Alfordai benchmark clip computer vision deep learning google image imagenet ml & data engineering neural networks news text
More from www.infoq.com / InfoQ - AI, ML & Data Engineering
Airbnb Open-Sources its ML Feature Platform Chronon
1 day, 3 hours ago |
www.infoq.com
Open Source Elastic's OpenTelemetry SDK for .NET
2 days, 11 hours ago |
www.infoq.com
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
IT Commercial Data Analyst - ESO
@ National Grid | Warwick, GB, CV34 6DA
Stagiaire Data Analyst – Banque Privée - Juillet 2024
@ Rothschild & Co | Paris (Messine-29)
Operations Research Scientist I - Network Optimization Focus
@ CSX | Jacksonville, FL, United States
Machine Learning Operations Engineer
@ Intellectsoft | Baku, Baku, Azerbaijan - Remote
Data Analyst
@ Health Care Service Corporation | Richardson Texas HQ (1001 E. Lookout Drive)