Artificial Intelligence Conference San Francisco 92/114

Artificial Intelligence Conference San Francisco 92/114

Avesh Singh 
Software Engineer, Cardiogram

Avesh Singh is an engineer at Cardiogram, a startup that applies deep learning to wearable data. Previously, Avesh worked at Nest Labs and Google. He holds a a BS and MS in computer science from Carnegie Mellon University.


1:45pm–2:25pm Tuesday, September 19, 2017
Deep learning with limited labeled data
Implementing AI
Location: Yosemite BC
Level: Intermediate
Secondary topics:  Data and training, Medicine

Avesh Singh (Cardiogram), Brandon Ballinger (Cardiogram)
Deep learning is fueled by large labeled datasets, but in domains like medicine, each label represents a human life at risk. Avesh Singh and Brandon Ballinger offer an overview of autoencoders, heuristic training, and few-shot learning, with an emphasis on practical tips to create high-performing models utilizing hundreds of thousands of unlabeled data points and only thousands of labeled points.