Abstract: 

We will build and tweak several vision classifiers together starting with perceptrons and building up to transfer learning and convolutional neural networks. We will investigate practical implications of tweaking loss functions, gradient descent algorithms, network architectures, data normalization, data augmentation and so on. This class is super hands on and practical and requires no math or experience with deep learning.

Bio: 

Stacey Svetlichnaya is deep learning engineer at Weights & Biases in San Francisco, CA, helping develop effective tools and patterns for deep learning. Previously a senior research engineer with Yahoo Vision & Machine Learning, working on image aesthetic quality and style classification, object recognition, photo caption generation, and emoji modeling. She has worked extensively on Flickr image search and data pipelines, as well as automating content discovery and recommendation. Prior to Flickr, she helped build a visual similarity search engine with LookFlow, which Yahoo acquired in 2013. Stacey holds a BS ‘11 and MS ’12 in Symbolic Systems from Stanford University.