Hype: Compositional Machine Learning and Hyperparameter Optimization
Hype is a proof-of-concept deep learning library, where you can perform optimization on compositional machine learning systems of many components, even when such components themselves internally perform optimization.
It is developed by AtΔ±lΔ±m GΓΌneΕ Baydin and Barak A. Pearlmutter, at the Brain and Computation Lab, National University of Ireland Maynooth.
This work is supported by Science Foundation Ireland grant 09/IN.1/I2637.
Please visit the project website for documentation and tutorials.
You can come and join the Gitter chat room, if you want to chat with us:
Project statistics
Current build status
License
Hype is released under the MIT license.