no code implementations • 18 Feb 2023 • Jordi de la Torre
In the image case, a progressive pixel corruption process is carried out by applying random noise, and a neural network is trained to revert each one of the corruption steps.
no code implementations • 18 Feb 2023 • Jordi de la Torre
VAEs are probabilistic graphical models based on neural networks that allow the coding of input data in a latent space formed by simpler probability distributions and the reconstruction, based on such latent variables, of the source data.
no code implementations • 18 Feb 2023 • Jordi de la Torre
Generative models model the probability distribution of a data set, but instead of providing a probability value, they generate new instances that are close to the original distribution.
no code implementations • 18 Feb 2023 • Jordi de la Torre
Transformers are a neural network architecture originally designed for natural language processing that it is now a mainstream tool for solving a wide variety of problems, including natural language processing, sound, image, reinforcement learning, and other problems with heterogeneous input data.
no code implementations • 23 Sep 2018 • Jordi de la Torre, Aida Valls, Domenec Puig, Pere Romero-Aroca
In this paper we go forward into the generation of explanations by identifying the independent causes that use a deep learning model for classifying an image into a certain class.
no code implementations • 21 Dec 2017 • Jordi de la Torre, Aida Valls, Domenec Puig
Deep neural network models have been proven to be very successful in image classification tasks, also for medical diagnosis, but their main concern is its lack of interpretability.