Loading view.
Week of Events
Nonlinear Embedding Methods in Modern Data Visualization: Theory & Practice
Learning and representing low-dimensional structures from noisy and possibly high-dimensional data is an indispensable component of modern data science. Recently, a special class of nonlinear embedding methods has become particularly influential, most notably, the t-distributed stochastic neighbor embedding (t-SNE) and the uniform manifold approximation and projection (UMAP). Despite their empirical success in many research fields,... Read more
LEHIGH VALLEY EXECUTIVE COMMITTEE MEETING – April
Executive Committee planning meeting for upcoming events. All ExCom's are Virtual. These are open to all members including students. At this time the meeting will be remote. Connection information will be sent out at 3:00pm on the day of the meeting to those who have registered. Please register for the meeting by noon of the... Read more
LEHIGH VALLEY EXECUTIVE COMMITTEE MEETING – April
Executive Committee planning meeting for upcoming events. All ExCom's are Virtual. These are open to all members including students. At this time the meeting will be remote. Connection information will be sent out at 3:00pm on the day of the meeting to those who have registered. Please register for the meeting by noon of the... Read more
-
Madhu Chinnambeti Presents: Retrieval Augmented Generation (RAG)
Madhu Chinnambeti Presents: Retrieval Augmented Generation (RAG)
[] Large Language Models (LLMs) are being used widely in current Generative AI systems. Unfortunately, LLMs demonstrate significant capabilities but face challenges such as hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of... Read more