Search Results for author: Gabriele Graffieti

Found 8 papers, 3 papers with code

On the challenges to learn from Natural Data Streams

no code implementations9 Jan 2023 Guido Borghi, Gabriele Graffieti, Davide Maltoni

In real-world contexts, sometimes data are available in form of Natural Data Streams, i. e. data characterized by a streaming nature, unbalanced distribution, data drift over a long time frame and strong correlation of samples in short time ranges.

Incremental Learning

Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning

no code implementations6 Jan 2023 Vincenzo Lomonaco, Lorenzo Pellegrini, Gabriele Graffieti, Davide Maltoni

In recent years we have witnessed a renewed interest in machine learning methodologies, especially for deep representation learning, that could overcome basic i. i. d.

class-incremental learning Incremental Learning +1

Generative Negative Replay for Continual Learning

no code implementations12 Apr 2022 Gabriele Graffieti, Davide Maltoni, Lorenzo Pellegrini, Vincenzo Lomonaco

Learning continually is a key aspect of intelligence and a necessary ability to solve many real-life problems.

Continual Learning

Is Class-Incremental Enough for Continual Learning?

no code implementations6 Dec 2021 Andrea Cossu, Gabriele Graffieti, Lorenzo Pellegrini, Davide Maltoni, Davide Bacciu, Antonio Carta, Vincenzo Lomonaco

The ability of a model to learn continually can be empirically assessed in different continual learning scenarios.

Continual Learning

Latent Replay for Real-Time Continual Learning

3 code implementations2 Dec 2019 Lorenzo Pellegrini, Gabriele Graffieti, Vincenzo Lomonaco, Davide Maltoni

Continual learning techniques, where complex models are incrementally trained on small batches of new data, can make the learning problem tractable even for CPU-only embedded devices enabling remarkable levels of adaptiveness and autonomy.

Continual Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.