Towards Neural Sparse Linear Solvers

no code implementations • 14 Mar 2022 • Luca Grementieri, Paolo Galeone

We propose neural sparse linear solvers, a deep learning framework to learn approximate solvers for sparse symmetric linear systems.

Learning to Grasp from 2.5D images: a Deep Reinforcement Learning Approach

no code implementations • 8 Aug 2019 • Alessia Bertugli, Paolo Galeone

Unity 3D allowed us to simulate a real-world setup, where a depth camera is placed in a fixed position and the stream of images is used by our policy network to learn how to solve the task.

Position reinforcement-learning +2

Adversarial Pixel-Level Generation of Semantic Images

no code implementations • 27 Jun 2019 • Emanuele Ghelfi, Paolo Galeone, Michele De Simoni, Federico Di Mattia

Generative Adversarial Networks (GANs) have obtained extraordinary success in the generation of realistic images, a domain where a lower pixel-level accuracy is acceptable.

Image Generation Semantic Segmentation

A Survey on GANs for Anomaly Detection

1 code implementation • 27 Jun 2019 • Federico Di Mattia, Paolo Galeone, Michele De Simoni, Emanuele Ghelfi

Anomaly detection is a significant problem faced in several research areas.

Anomaly Detection