WiMLDS x Lyft Machine Learning Talks

IMPORTANT Please also RSVP on Lyft's page here (full names/email needed for security): https://lyftwimldslightning.splashthat.com/

Schedule:

6:00 Arrival and networking
6:30 Welcome note by WiMLDS and Lyft
6:40 1st talk: "API Design Stories"
7:00 2nd talk: "Some insights into interpretability of machine learning algorithms and applications to risk management"
7:20 3rd talk: "Perception for Autonomous Cars"
7:40 4th talk: "Just ask: Designing intent-driven algos"
8:00 Mix and mingle
8:30 Event ends

1st talk: API Design Stories

Hear stories about successes and failures designing and building an API for Bayesian optimization as a service. Walk away from the talk with lessons and techniques you can incorporate into your own work.

By: Alexandra Johnson, AI Product Manager @ Citrine Informatics

Alexandra (Twitter: @alexandraj777) is an AI Product Manager at Citrine Informatics, and she loves creating simple and easy to use interfaces for complicated ML products. Previously, she was the Platform Tech Lead at SigOpt, where she and her team worked on productizing Bayesian optimization as a service. Her undergraduate degree is in Computer Science, from Carnegie Mellon University. She is based out of San Francisco and is the co-organizer of the Bay Area chapter of Women in Machine Learning and Data Science.

2nd talk: Some insights into interpretability of machine learning algorithms and applications to risk management
By: Jie Chen, Managing Director @ Wells Fargo

The “black box” nature of machine learning (ML) models have limited their widespread adoption in banking and finance. We provide a framework and a suite of algorithms and associated visualization tools that help to resolve the opaqueness of ML algorithms.

Jie Chen is Managing Director in the Advanced Technologies for Modeling (AToM) Group of Corporate Model Risk at Wells Fargo. She is leading the Statistics and Machine Learning team, focusing on development of cutting-edge models, algorithms, and a computing platform to advance the Bank’s practice in the areas of credit, operational, and market risk management.

3rd talk: Perception for Autonomous Cars
By: Anastasia Dubrovina, Software Engineer @ Lyft Level 5

In this talk, I will review the challenges involved in building the perception stack for an autonomous vehicle, and how state-of-the-art neural network models can be utilized in the perception pipeline to allow self-driving cars understand their surroundings on the road.

Anastasia is a Software Engineer at the Perception Team at Level 5 - the Self-Driving Division at Lyft. Anastasia completed her Postdoc at Stanford University, where she worked on machine learning applications for 3D shape analysis, synthesis and completion. Anastasia received a PhD in Computer Science from the Technion - the Israeli Institute of Technology.

4th talk: Just ask: Designing intent-driven algos
Anna Schneider, Data Science Manager @ Stitch Fix

Classic recommender systems are great for answering the question “what does a user want in general?”. However, they only get you partway to an answer to “what does a user want right now?”. To close the gap, it helps to capture and act on explicit user intent. I’ll share examples of this paradigm at Stitch Fix, and the resulting changes to our algorithms and architectures.

Anna Schneider (@windupanna) is a Data Science Manager on the Merch Algorithms team at Stitch Fix. Her team uses ML, OR, HCI, experimentation, and more to recommend how Stitch Fix sources half its inventory. Past lives include co-founding a clean energy data startup, earning a PhD in biophysics from UC Berkeley, and co-organizing the Unconscious Bias Project.