Play all

[] Ben's intro

[] Generative AI in Molecule Discovery

[] Molecule

[] Chemical Language Models

[] Smile representation

[] Graph representation

[] Chemical Language Models use cases and its challenges

[] Molecular Innovation

[] Large Language Models

[] RAG use case

[] Leveraging the RAG use case

[] Optimizing Gen AI in Call Center Applications

[] Call Center Analysis Goals

[] Challenges

[] Pipeline and Architecture

[] Application

[] Calls analysis

[] OpenAI for transcription

[] Speech diarization using Silver VAD

[] Distributed processing accelerates model and data handling

[] Text analyzed for quiz creation and polling

[] Large language models for general knowledge extraction

[] Experience in project management with various tools

[] Wrap up

Description:

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore innovative applications of Generative AI beyond text in this 55-minute MLOps Community Mini Summit talk. Dive into two fascinating use cases: molecule discovery for pharmaceutical and chemical industries, and call center optimization. Learn how Chemical Language Models and graph representations are revolutionizing the search for new molecules, potentially leading to better treatments and eco-friendly products. Discover the challenges and solutions in implementing Gen AI for call center applications, including maximizing GPU utilization, speeding up pipelines, and transitioning from proof-of-concept to production. Gain insights into leveraging RAG (Retrieval-Augmented Generation), distributed processing, and large language models for knowledge extraction in real-world scenarios. Perfect for data scientists, machine learning engineers, and anyone interested in cutting-edge AI applications in industry.

Innovative Gen AI Applications: Beyond Text - MLOps Mini Summit 5

MLOps.community

Add to list

#Computer Science #Artificial Intelligence #Generative AI #Machine Learning #MLOps #High Performance Computing #Parallel Computing #Parallelization #Retrieval Augmented Generation (RAG)