| |
AI, ML & Data Science Meetup
|
| With Reid Pryzant (Sr Research Scientist, Microsoft), Nora Gourmelon (Researcher, Friedrich-Alexander-University Erlangen-Nuremberg), David Mezzetti (Founder, NeuML). |
| Venue, Online, San Francisco |
|
Oct 05 (Thu) , 2023 @ 10:00 AM
| |
FREE |
|
|
|
|
|
|
|
|
| |
| DETAILS |
|
Zoom Link
https://voxel51.com/computer-vision-events/october-ai-machine-learning-data-science-meetup/
Glacier Monitoring with Computer Vision Models
The temporal variability of marine-terminating glacier front positions provides valuable information on the state of the glaciers. Therefore, the position of these fronts is an important parameter influencing the accuracy of climate models. To obtain the position, satellite imagery has traditionally been analyzed by hand. As the amount of satellite imagery & the need for accurate climate models is increasing, deep learning techniques are applied to extract the glacier front position from satellite images. In this talk, state-of-the-art models for this purpose will be discussed.
Nora Gourmelon is a PhD candidate in Computer Science at the Friedrich-Alexander-Universitt Erlangen-Nrnberg working on AI for Earth. Her main focus lies on the segmentation of glacier calving fronts in Synthetic Aperture Radar (SAR) satellite imagery.
Automatic Prompt Optimization with Gradient Descent & Beam Search
Large Language Models (LLMs) have shown impressive performance but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a simple & nonparametric solution to this problem, Automatic Prompt Optimization (APO), which is inspired by numerical gradient descent to automatically improve prompts, assuming access to training data & an LLM API. Our experiments suggest this method can outperform prior prompt editing techniques & improve an initial prompt's performance by up to 31%, by using data to rewrite vague task descriptions into more precise annotation instructions.
Reid Pryzant is a Senior Research Scientist at Microsoft, & former Computer Science PhD at Stanford University advised by Dan Jurafsky. His work has won outstanding research awards from CVPR, AAAI, & the National Science Foundation.
Build Natural Language Applications with txtai
This talk will introduce txtai & show how it can be used for semantic search, LLM orchestration & language model workflows. An overview of the embeddings database architecture will be discussed along with how vector indexes (sparse & dense), graph networks & relational databases connect together. Example use cases will cover SQL-driven vector search, topic modeling & retrieval augmented generation.
David Mezzetti is the founder of NeuML, the company behind txtai. He is building a suite of open-source, easy-to-use, semantic search & workflow applications. Dave previously co-founded & built Data Works into a 50+ person well-respected software services company leading to a successful acquisition.
|
|
|
|
|
|
|
|
