Machine Learning

PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks

In this paper, we present PARTIME, a software library written in Python and based on PyTorch, designed specifically to speed up neural networks whenever data is continuously streamed over time, for both learning and inference. Existing libraries are …

PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks

An implementation of Pipeline Parallelism for Real-Time Online Learning

Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented from …

Messing Up 3D Virtual Environments: Transferable Adversarial 3D Objects

In the last few years, the scientific community showed a remarkable and increasing interest towards 3D Virtual Environments, training and testing Machine Learning-based models in realistic virtual worlds. On one hand, these environments could also …

Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments

Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in creating …

SAILenv at ICPR2020

SAILenv was presented at ICPR2020

Learning Sidarthe at SOPHI.A Summit

Learning Sidarthe project was present at the SOPHI.A Summit 2020

Object Detection with V-DAENY

A Dataset Generator powered by a modded version of GTA V

Face Recognition App

A face recognition app for android powered by Machine Learning

SAILenv

A virtual environment for generating fully annotated video streams.