Welcome!

Great news! The Zuru ML Team (me, Federico Di Mattia, Paolo Galeone, Michele De Simoni) will present the tutorial: “Deep Diving into GANs: From Theory to Production with TensorFlow 2.0” at EuroSciPy in Bilbao, the 2nd of September 2019. This tutorial builds upon the PyConX (see also... [Read More]

AshPy is a TensorFlow 2.0 library for (distributed) training, evaluation, model selection, and fast prototyping. It is designed to ease the burden of setting up all the nuances of the architectures built to train complex custom deep learning models. AshPy, why? Ashpy provides already prepared trainers for classifier... [Read More]

The paper Toward Multimodal Image-to-Image Translation (Zhu et al., 2017) faces the problem of multimodal image-to-image translation in a principled way. The same problem is faced in (Isola et al., 2016) (pix2pix) but in a not-so-effective manner (enabling Dropout at inference time). In... [Read More]

This format is deliberately inspired by Adrian Colyer, Denny Britz and Daniel Takeshi. The series Paper Notes will contain the notes about papers I’ve read. This can be useful for people trying to understand better some mysterious paper and it can be very useful for me to... [Read More]

Paper Poster Slides Code Most of the problems tackled by Reinforcement Learning are typically modeled as Markov Decision Processes in which the environment is considered a fixed... [Read More]