![]() ![]() Gaurav Singh, Solutions Architect, AWS India In this session, we explain how to generate innovative and useful content on a large scale and maximize the potential of generative AI while addressing the concerns around responsible AI. With the proliferation of unstructured data that is incorporated into new algorithms and applications using generative AI, it is imperative to establish a strategy for responsible AI that can withstand this new age. Organizations attempt to address these challenges through complex governance and oversight processes, rigorous audits, and filters on the generated content and constantly solicit user feedback but this requires a lot of effort, time, and resources. They raise new issues around fairness, toxicity, intellectual property, hallucinations, and privacy. Generative AI models that produce open-ended and unconstrained content pose additional challenges for responsible AI. Speaker: Arun Balaji, Principal Prototyping Engineer, AWS IndiaĪddressing Responsible AI and AWS generative AI offerings (Level 200) ![]() We explain when and how to use advanced prompt engineering, fine-tuning, and RLHF options to improve the results and demonstrate one of the patterns. We explore some of the solutions that use generative AI models in conjunction with AWS building blocks such as Amazon SageMaker and Amazon SageMaker JumpStart to solve common use cases including question and answer, summarization, simplification, and tone augmentation. prompt engineering, to improve generative AI performance. This session covers the guidelines on when to apply RAG, vs. It opens up the possibility of developing a wide range of applications for a variety of use cases. Generative AI offers the potential to transform the way we interact, as you can create new content that are both realistic and creative by learning from large datasets of text, images, and code. Generative AI patterns on AWS: Exploring modern applications with generative AI (Level 200) Tuan Huynh, Cloud Architect, AWS Professional Services Kush Tiwari, Senior Applications Architect, AWS Professional Services We also review how to incorporate AI and machine learning in the modernization process, by showcasing how Microservice Extractor leverages AI-powered recommendations for valuable insights to optimize the microservices architecture. to facilitate extraction of microservices from monoliths. We share how to utilize AWS Microservice Extractor for. Learn about the modernization solutions for applications built on Microsoft technologies and AWS tools that support Microsoft workload migration to the cloud. In this session, we outline the challenges of transitioning from monoliths to microservices and benefits of microservices. Moving from monolithic to microservices involves multiple manual steps, which requires domain level knowledge and significant effort to manage this transition. ![]() Speaker: Katherine Vishnevskaya, Solutions Architect, AWSĪccelerate transformation on.NET monolith applications to microservices with AI and machine learning (Level 300) The session also covers the different pathways you can use to minimize your code and cost. Understand how AWS Step Functions integrates with other AWS services, letting you call each service's API actions from your workflow. We also walk through the key features of AWS Step Functions which enable you to build distributed applications, automate processes, orchestrate microservices, as well as create data and machine learning (ML) pipelines. Learn how this low-code, visual workflow service, makes it fun for you to work with and easy to adopt. We share how AWS Step Functions, allows you to centrally manage a workflow by breaking it into multiple steps, adding flow logic, tracking the inputs and outputs between the steps. AWS Step Functions: When to use and how to get the most out of it (Level 200)ĪWS Step Functions is a service that enables you to coordinate your workflows so that your application development is faster and more intuitive. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |