Karen Ullrich's Projects
A minimal implementation of a VAE with BinConcrete (relaxed Bernoulli) latent distribution in TensorFlow.
Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables
Experiments for continuous to binary and back
A toolbox for analyzing high dimensionality issues in machine learning. Written in Python.
Models and examples built with TensorFlow
Official code accompanying the arXiv paper Compressing Multisets with Large Alphabets
Tensors and Dynamic neural networks in Python with strong GPU acceleration
This code accompanies "Differentiable probabilistic models of scientific imaging with the Fourier slice theorem", UAI 2019
Turning float tensors to binary tensors according to IEEE-754 standard.
Spearmint Bayesian optimization codebase
Spearmint uses Gaussian Processes to automatically optimize hyper parameter. This is a fork of Spearmint for the deep learning community. More specifically, it provides support for Theano users.
Computation using data flow graphs for scalable machine learning
Optimizing GPU-meta-programming code generating array oriented optimizing math compiler in Python
A tutorial on 'Soft weight-sharing for Neural Network compression' published at ICLR2017
A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).
Homepage of UVA IAI