Focused crawls are collections of frequently-updated webcrawl data from narrow (as opposed to broad or wide) web crawls, often focused on a single domain or subdomain.
Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learning using automatic differentiation.
This project contains examples which demonstrate how to deploy analytic models to mission-critical, scalable production environments leveraging Apache Kafka and its Streams API. Models are built with Python, H2O, TensorFlow, Keras, DeepLearning4 and other technologies.
Federated Learning: Parameter Server doing aggregation of updates to a model coming from clients participating in a Federated Learning setup. See also the Android application companion at https://github.com/mccorby/PhotoLabeller
In photographic media, faces are often obfuscated to protect the identity of those pictured. This obfuscation process is done by removing details from the photograph in order to reduce the identifying facial features. However, these obfuscated images may still contain enough details such that the original features may be able to be recovered. In this project we will examine different neural networks to reconstruct obfuscated images of human faces.
