AI inference is the process of using a trained machine learning model to make predictions on new, unseen data by applying learned patterns. This course is designed for developers, data scientists, and ML engineers interested in quickly deploying AI inference services on Cloud Run. It is useful for those familiar with cloud-based serverless application deployment solutions, but who may not have experience with running AI inference using Google Cloud serverless products. The course includes examples that deploys a model for AI inference with GPUs and integrates gen AI apps with data storage services.
In this course, you learn how Gemini, a generative AI-powered collaborator from Google Cloud, helps you use Google products and services to develop, test, deploy, and manage applications. With help from Gemini, you learn how to develop and build a web application, fix errors in the application, develop tests, and query data. Using a hands-on lab, you experience how Gemini improves the software development lifecycle (SDLC). Duet AI was renamed to Gemini, our next-generation model.
Bu kurs, MLOps ekiplerinin üretken yapay zeka modellerini dağıtırken ve yönetirken karşılaştığı zorlukların üstesinden gelmek için gereken bilgi ve araçları sağlamaktadır. Ayrıca yapay zeka ekiplerinin, MLOps süreçlerini kolaylaştırıp üretken yapay zeka projelerinde başarıya ulaşması için Vertex AI'ın nasıl yardımcı olduğunu öğrenmenizi amaçlamaktadır.