
Welcome to the in-person monthly ML meetup in Seattle/Bellevue. Join us for deep dive tech talks on AI/ML/Data, food/drink, networking with speakers&peer developers, and win lucky draw prizes.
Agenda (PDT):
* 5:00pm~5:30pm: Checkin, Food/drink and networking
* 5:30pm~5:40pm: Welcome/community update/Sponsor intro
* 5:40pm~7:00pm: Tech talks
* 7:00pm: Opening discussion, Lucky draw and Mixer
Tech Talk 1: Declarative Reasoning with Timelines: The Next Step in Event Processing
Speaker: Ben Chambers, ML CTO @Datastax/Kaskada
Abstract: At the heart of modern data processing lies events. Events describe the roughest, most complete picture available of what has happened in the world, and practically every form of data processing ultimately begins with events.
While the power of event processing has increased since the emergence of streaming data processing, current systems are still difficult to use when working on problems that deal with time and order, such as predictive AI/ML. Handling these problems requires a new kind of query language - a way to declaratively reason about events over time.
In this talk, we introduce the concept of timelines. Timelines are an intuitive abstraction for reasoning about temporal values. They support a broad range of useful operations which can be efficiently computed at scale. We will demonstrate the power and differentiation of timelines:
- How timelines allow declarative queries over events and time in a simple and intuitive manner
- Why timelines are ideal for applications such as behavioral predictions, trend analysis, and forecasting, and how existing solutions such as streaming SQL fall short.
- How to execute timeline based queries using the open-source Kaskada event-processing engine.
Tech Talk 2: Caching for ChatGPT and More with Vector Databases
Speaker: Yujian Tang, Developer @Zilliz
Abstract: A few months ago, AI was “hip” and “cool”, but it wasn’t mainstream. Then, ChatGPT single handedly put AI, and large language models (LLMs) in particular, on everyone’s radar. Since then, people have made all sorts of applications using GPT and its extensions including a bot to automatically order pizza.
Despite all the potential of LLMs, they still have some limitations. In this talk, we will cover how to overcome some of these limitations by using vector databases to inject domain specific knowledge. We will also share some open source tools that cache LLM responses helping you decrease the cost and increase the performance of your LLM app.
Tech Talk 3: Discovering outliers in global health data
Speaker: Sasha Aravkin, Professor @UW
Abstract: Risk-outcome analysis is a key area in epidemiology and global health. For example, how strong is the relationship between red meat consumption and risk of heart disease, based on all available data? How does it compare to the impact of smoking on risk of lung cancer?
In this talk I will share some recent work and interactive results in understanding these relationships. I also want to highlight a particularly versatile approach to outlier detection and removal, and show how that method generalizes to other domains including machine learning.
Venue:
Microsoft Reactor, 3709 157th Ave NE, Redmond, WA
- Driving direction: follow Google Map
- Free parking
- Car pool: post to community discussion group on slack (#seattle channel)
Lucky draw
We will raffle winners for prizes during the event. To enter the lucky draw, share the meetup on social media:
#aicampseattle Join the monthly ML meetup in Seattle by @aicampai to learn AI, ML, Data and Cloud technology with tech leads and industry experts. Free join in person: https://www.aicamp.ai/event/eventdetails/W2023050217
Community on Slack
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (join the #seattle channel)