Top 10 ODSC West Talks Every Data Scientist Should See

ODSC West 2022 is only a little over a month away and we are busy putting the final touches on our lineup of hands-on training sessions, expert-led workshops, and engaging talks. With 300+ hours of content, there will be more than enough to explore. Enjoy this sneak peek of 10 of the talks that will be at the conference.

Human-Friendly, Production-Ready Data Science with Metaflow

Ville Tuulos | Co-founder & CEO | Outerbounds

Join this session to explore how Metaflow, an open-source framework developed at Netflix, enables data scientists to independently build and put into production end-to-end machine learning applications and workflows. You’ll leave this talk with:

• An understanding of what’s included in a modern ML infrastructure stack
• How Metaflow and other tools can help increase the productivity of your data science team
• How to successfully integrate a full stack of ML infrastructure into your existing policies and systems

Building Production-Ready Recommender Systems with Feast

Danny Chiao | Engineering Lead | Tecton

Although a popular component in modern applications and systems, recommender systems are frequently difficult to build and maintain. Common challenges include data leakage, data dependencies, and data and models that change frequently. Join this talk to explore how feature stores can help resolve many of these challenges.

Artificial Intelligence Can Learn from Data. But Can It Learn to Reason?

Guy Van den Broeck, PhD | Director, Associate Professor | StarAI (Statistical and Relational Artificial Intelligence Lab), UCLA

As artificial intelligence is used for more and more applications, the expectation that it can be utilized for more complex tasks, such as mental health services, also grows. This session will explore whether it is possible to learn to reason from data, and how that might be accomplished.

Search and Discovery in News and Research

Dr. Anju Kambadur | Head of AI Engineering | Bloomberg

Join this talk to discover how Bloomberg has leveraged three areas in AI, NLP, machine learning and deep learning, and information search and retrieval to create a search and discovery system for financial news and research. Using this expertise, Bloomberg has been able to help its clients parse unstructured data for insights.

Detecting Changes Over Time with Bayesian Change Point Analysis in R

Aric LaBarr, PhD | Associate Professor of Analytics | Institute for Advanced Analytics at NC State University

Did my data change after a certain intervention? This is a common question with data observed over time. Classical statistical and engineering approaches include control charts to see if the series falls outside of the normal boundaries of expected data. A Bayesian approach to this problem calculates the probability that the data series changes at every point along the series. Bayesian change point analysis allows the analyst to evaluate a whole series and look where the highest probability of change occurred.

MLOps for Deep Learning

Diego Klabjan, PhD | Professor | Northwestern University / Yegna Jambunath | MLOps Research Specialist | Northwestern University

Join this session to learn more about how to detect drift in a model using an ensemble technique. You’ll also explore two of the challenges that complicate life-long model retraining: efficient retraining and catastrophic forgetting.

Responsible AI Is Not an Option

Scott Zoldi, PhD | Chief Analytics Officer | FICO

Join this session to learn how to identify and mitigate the risks associated with using AI in business. He’ll utilize his extensive experience to highlight the importance of AI fairness and bias in an approachable and easily understood way.

Human Factors of Explainable AI

Meg Kurdziolek, PhD | Sr. UX Researcher | Google

In this session, you’ll learn about the factors that cause different stakeholders and audiences to engage with and interpret machine learning models and explainable AI in different ways. You’ll also leave with a framework for how to approach assessing and designing interpretable ML systems.

Operationalizing Organizational Knowledge with Data-Centric AI

Alex Ratner, PhD | Assistant Professor, Co-founder & CEO | UW, Snorkel AI

In this session, you’ll delve into data-centric AI and its supposition that data is the central factor that determines whether a model or application succeeds or fails in AI. You’ll explore how weak supervision improves data-centric workflows and even acts as an API for rich organizational knowledge sources.

Impact of Data Science on Social Media Data

Jyotika Singh | Director of Data Science | Placemakr

Join this session to explore how data is generated on social media and how it is consumed by data scientists and other professions for data intelligence, data analytics, recommendation systems, chatbots, and more. This talk will also look at how biases affect machine learning models and how to approach this challenge going forward.

Register for ODSC West 2022

Above are just a few of the talks that will be featured at ODSC West this November 1st-3rd. If you want to learn more about MLOps, data engineering, machine learning, NLP, deep learning, responsible AI, and more, be sure to get your ODSC West Pass soon–40% off all conference passes ends Friday!

Originally posted on OpenDataScience.com

Read more data science articles on OpenDataScience.com, including tutorials and guides from beginner to advanced levels! Subscribe to our weekly newsletter here and receive the latest news every Thursday. You can also get data science training on-demand wherever you are with our Ai+ Training platform. Subscribe to our fast-growing Medium Publication too, the ODSC Journal, and inquire about becoming a writer.