I've been working on a side project this summer to build my own guitar amplifier, because I'm not particularly satisfied with the tone I get from the commercial guitar amps (Read more...)
When evaluating a machine learning model, most practitioners simply apply the standard precision/recall formulas to whatever test set they have. The results can be wildly (Read more...)
In 2016, researchers from Google Brain published a paper showing how neural networks can learn symmetric encryption to protect information from other AI attackers. (Read more...)
The encoding vector of a Conditional Variational Autoencoder (CVAE) is comprised of two components - the style encoding, and the conditioning vector. This visualization explores (Read more...)
We saw in Intro to Autoencoders how the encoding space was a non-convex manifold, which makes basic autoencoders a poor choice for generative models. Variational autoencoders fix this issue by ensuring (Read more...)