4 papers
Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
J. D. Curtó, I. C. Zarza, Kris Kitani +2
Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning tha…
High-resolution Deep Convolutional Generative Adversarial Networks
J. D. Curtó, I. C. Zarza, Fernando de la Torre +2
Generative Adversarial Networks (GANs) [Goodfellow et al. 2014] convergence in a high-resolution setting with a computational constrain of GPU memory capacity has been beset with d…
Segmentation of Objects by Hashing
J. D. Curtó, I. C. Zarza, Alex Smola +1
We propose a novel approach to address the problem of Simultaneous Detection and Segmentation introduced in [Hariharan et al 2014]. Using the hierarchical structures first presente…
McKernel: A Library for Approximate Kernel Expansions in Log-linear Time
J. D. Curtó, I. C. Zarza, Feng Yang +4
McKernel introduces a framework to use kernel approximates in the mini-batch setting with Stochastic Gradient Descent (SGD) as an alternative to Deep Learning. Based on Random Kitc…