Ayda Farhadi

Senior Data Scientist at UPS

Ayda Farhadi is an experienced Data Scientist with a demonstrated history of working in the hospital & health care industry. She has executive experience in designing solutions for analytical problems and utilizing different programming languages. She is passionate about using new technologies. She has strong information technology professional with a Ph.D. degree focused in Computer Science from The University of Georgia. Her Thesis was about Transfer Learning in Healthcare, and she is interested in utilizing deep transfer learning in other applications to improve lives and business.

WATCH LIVE: February 16 @ 1:50PM – 2:10PM ET

Transfer Learning: Applications in the Real World

Training machine learning models can be challenging data science tasks. The training algorithms might not work as intended, training times can take too long, or training data can be problematic. Transfer learning is one of those techniques to make training easier. Humans have an inherent ability to transfer knowledge across tasks. What we acquire as knowledge while learning about one task, we utilize in the same way to solve related tasks. In similar ways, transfer learning can provide data scientists to transfer insights gained from a machine learning task into a similar one. By that, they can shorten machine learning model training time and rely on fewer data points. Some important applications of Transfer learning are: Learning from simulations (such as self-driving cars), Adapting to a new domain (Healthcare), and transferring knowledge across languages (English). Since the publication of the transfer learning survey paper by Sinno Pan in 2010, there have been over 700 academic papers written addressing advancements and innovations on the subject of transfer learning in healthcare. Transfer learning in healthcare is used in multiple contexts to make a diagnosis of dierent types of disease. The aspect of information transfer is categorized into four general Transfer learning categories including, Transfer learning in Healthcare through instances, Transfer learning in Healthcare through features, Transfer learning in Healthcare through neural Networks, and Transfer learning in Healthcare through adversarial learning.