AI Meetup at AWS: Generative AI, LLMs and GNN

Pre-registration is required for admission: https://www.aicamp.ai/event/eventdetails/W2023081715
(Venue security may not let you in if you don't pre-register at the link above)

Welcome to our in-person ML monthly meetup in Chicago, in collaboration with AWS. Join us for deep dive tech talks on AI/ML, food/drink, networking with speakers&peers developers, and win lucky draw prizes.

Agenda (CDT):
* 4:00pm~5:00pm: Checkin, Food/drink and networking
* 5:00pm~5:10pm: Welcome/community update/Sponsor intro
* 5:10pm~7:10pm: Tech talks
* 7:10pm: Open discussion & Mixer

Tech Talk 1: Operationalize Fraud Detection using Graph Neural Network(GNN) in Production
Speaker: Puneet Rawal @AWS
**Abstract:**In this session you will learn about running production scale fraud detection using GNN, Amazon Neptune and SageMaker. We will be using customer identity and credit card transactions to train model, tune hyper-parameters, deploy GNN model and run real-time inference to detect fraud as it is happening. Attendees will walk out with working example of full scale application using MLOps pipeline and SageMaker endpoints.

Tech Talk 2: Transforming Conversational AI with Generative AI and Large Language Models
Speaker: Swagat Kulkarni @AWS
**Abstract:**This session explores the transformative impact of Generative AI (GenAI) and Large Language Models (LLMs) on conversational AI applications. With the advent of GenAI models, developers and enterprises can effectively tackle complex challenges in natural language processing and understanding. The session highlights the benefits of LLMs, such as creating compelling conversational experiences for customer service and enhancing employee productivity. The session introduces the Retrieval Augmented Generation (RAG) technique, which retrieves relevant information from enterprise knowledge bases and combines it with user requests to improve response accuracy. Attendees will gain insights into optimizing LLM usage, addressing prompt length limitations, and leveraging GenAI for more intelligent conversational interactions.

Tech Talk 3: Fine-tune large language models using SageMaker distributed training libraries
Speaker: Kanwaljit Khurm @AWS
**Abstract:**Learn how to fine-tune large language models on Amazon SageMaker to build your generative AI applications. We will explore popular generative AI use cases and mechanism to fine-tune large language models using SageMaker distributed data parallel and model parallel libraries.

-------

• Contact us to submit topics and/or sponsor the meetup on venue/food/swags/prizes. https://forms.gle/JkMt91CZRtoJBSFUA
• Community on Slack for events chat, speakers office hour and learning resources, job openings and projects collaboration. join slack (search and join #chicago channel)