Level Up Your Machine Learning Lifecycle
By Dr. Yaqi Chen, Machine Learning Strategy Lead
How does an image-processing application that classifies animals accelerate the development of a vehicle license plate number detector? In this talk, Dr. Yaqi Chen, Lead Data Scientist at Object Computing, demonstrates how ML practitioners can achieve a level of scalability and generalization that opens up a vast landscape of possibilities. Using a real-world example, she illustrates how a series of plug-and-play modules built across the data, model, and deployment stages dramatically simplify the process of building an end-to-end ML project. If you could benefit from an ML lifecycle framework that allows you to continue tackling complicated real-world challenges, while enjoying shorter development time, simplified bug isolation, and a cleaner code base, this talk is for you!
This presentation was recorded at the Strange Loop 2022 Conference
ABOUT DR. YAQI CHEN
Yaqi received her PhD from Washington University in 2014 with a research focus in Algorithm Development and Information Theory for Medical Imaging. After graduating she joined a leading digital agricultural company where she led a group of data scientists and engineers and established a Machine Learning framework by leveraging imagery and geospatial data to improve on-farm productivity. Today she is working with clients across multiple industries as Object Computing continues to help companies simplify complex business processes with machine learning and data science. Additionally, she has also been a keen advocate of Women in Data Science as both a leader and mentor.
Software Engineering Tech Trends (SETT) is a regular publication featuring emerging trends in software engineering.