The Science Behind InterpretML: Explainable Boosting Machine
Learn more about the research that powers InterpretML from Explainable Boosting Machine creator, Rich Caurana from Microsoft Research. Learn More: Azure Blog Responsible ML Azure ML
Objects are the secret key to revealing the world between vision and language
Humans perceive the world through many channels, such as images viewed by the eyes or voices heard by the ears. Though any individual channel might be incomplete or noisy, humans can naturally align and fuse…
A Locally Adaptive Interpretable Regression
Diving into Deep InfoMax with Dr. Devon Hjelm
Dr. Devon Hjelm is a senior researcher at the Microsoft Research lab in Montreal, and on the podcast, he joins me to dive deep into his research on Deep InfoMax, a novel self-supervised learning approach…
Project FLUTE
A novel framework for training models in a Federated Learning fashion. One of the novelties of the project is the first attempt to introduce Federated Learning in Speech Recognition tasks. Besides the novelty of the…
Deep Neural Methods for Retrieval by Bhaskar Mitra (Guest lecture at Emory University)
In this follow up lecture, we will be covering fundamental deep neural architectures for retrieval and ranking applications in information retrieval. Slides: https://www.slideshare.net/BhaskarMitra3/deep-neural-methods-for-retrieval Previous lecture: https://www.youtube.com/watch?v=1uut7IGStw8