Search Results for author: Antonio Carta

Found 24 papers, 13 papers with code

Avalanche: A PyTorch Library for Deep Continual Learning

1 code implementation2 Feb 2023 Antonio Carta, Lorenzo Pellegrini, Andrea Cossu, Hamed Hemati, Vincenzo Lomonaco

Continual learning is the problem of learning from a nonstationary stream of data, a fundamental issue for sustainable and efficient training of deep neural networks over time.

Continual Learning

Class-Incremental Learning with Repetition

no code implementations26 Jan 2023 Hamed Hemati, Andrea Cossu, Antonio Carta, Julio Hurtado, Lorenzo Pellegrini, Davide Bacciu, Vincenzo Lomonaco, Damian Borth

We focus on the family of Class-Incremental with Repetition (CIR) scenarios, where repetition is embedded in the definition of the stream.

Class Incremental Learning Incremental Learning

Sample Condensation in Online Continual Learning

1 code implementation23 Jun 2022 Mattia Sangermano, Antonio Carta, Andrea Cossu, Davide Bacciu

A popular solution in these scenario is to use a small memory to retain old data and rehearse them over time.

Continual Learning

Continual Pre-Training Mitigates Forgetting in Language and Vision

1 code implementation19 May 2022 Andrea Cossu, Tinne Tuytelaars, Antonio Carta, Lucia Passaro, Vincenzo Lomonaco, Davide Bacciu

We formalize and investigate the characteristics of the continual pre-training scenario in both language and vision environments, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks.

Continual Learning Continual Pretraining

Practical Recommendations for Replay-based Continual Learning Methods

no code implementations19 Mar 2022 Gabriele Merlin, Vincenzo Lomonaco, Andrea Cossu, Antonio Carta, Davide Bacciu

Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge.

Continual Learning Data Augmentation

Avalanche RL: a Continual Reinforcement Learning Library

1 code implementation28 Feb 2022 Nicolò Lucchesi, Antonio Carta, Vincenzo Lomonaco, Davide Bacciu

Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences).

Continual Learning OpenAI Gym +2

AI-as-a-Service Toolkit for Human-Centered Intelligence in Autonomous Driving

no code implementations3 Feb 2022 Valerio De Caro, Saira Bano, Achilles Machumilane, Alberto Gotta, Pietro Cassará, Antonio Carta, Rudy Semola, Christos Sardianos, Christos Chronis, Iraklis Varlamis, Konstantinos Tserpes, Vincenzo Lomonaco, Claudio Gallicchio, Davide Bacciu

This paper presents a proof-of-concept implementation of the AI-as-a-Service toolkit developed within the H2020 TEACHING project and designed to implement an autonomous driving personalization system according to the output of an automatic driver's stress recognition algorithm, both of them realizing a Cyber-Physical System of Systems.

Autonomous Driving reinforcement-learning +1

Ex-Model: Continual Learning from a Stream of Trained Models

1 code implementation13 Dec 2021 Antonio Carta, Andrea Cossu, Vincenzo Lomonaco, Davide Bacciu

Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years.

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

Continual Learning with Echo State Networks

1 code implementation17 May 2021 Andrea Cossu, Davide Bacciu, Antonio Carta, Claudio Gallicchio, Vincenzo Lomonaco

Continual Learning (CL) refers to a learning setup where data is non stationary and the model has to learn without forgetting existing knowledge.

Continual Learning

Distilled Replay: Overcoming Forgetting through Synthetic Samples

2 code implementations29 Mar 2021 Andrea Rosasco, Antonio Carta, Andrea Cossu, Vincenzo Lomonaco, Davide Bacciu

Replay strategies are Continual Learning techniques which mitigate catastrophic forgetting by keeping a buffer of patterns from previous experiences, which are interleaved with new data during training.

Continual Learning

Continual Learning for Recurrent Neural Networks: an Empirical Evaluation

no code implementations12 Mar 2021 Andrea Cossu, Antonio Carta, Vincenzo Lomonaco, Davide Bacciu

We propose two new benchmarks for CL with sequential data based on existing datasets, whose characteristics resemble real-world applications.

Continual Learning

Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory

1 code implementation29 Jun 2020 Antonio Carta, Alessandro Sperduti, Davide Bacciu

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales.

speech-recognition Speech Recognition

Continual Learning with Gated Incremental Memories for sequential data processing

1 code implementation8 Apr 2020 Andrea Cossu, Antonio Carta, Davide Bacciu

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions.

Continual Learning Reinforcement Learning (RL)

Encoding-based Memory Modules for Recurrent Neural Networks

no code implementations31 Jan 2020 Antonio Carta, Alessandro Sperduti, Davide Bacciu

The experimental results on synthetic and real-world datasets show that specializing the training algorithm to train the memorization component always improves the final performance whenever the memorization of long sequences is necessary to solve the problem.


Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders

2 code implementations15 Jan 2020 Andrea Valenti, Antonio Carta, Davide Bacciu

Through the paper, we show how Gaussian mixtures taking into account music metadata information can be used as an effective prior for the autoencoder latent space, introducing the first Music Adversarial Autoencoder (MusAE).

Music Modeling

Autoencoder-based Initialization for Recurrent Neural Networks with a Linear Memory

no code implementations25 Sep 2019 Antonio Carta, Alessandro Sperduti, Davide Bacciu

We propose an initialization schema that sets the weights of a recurrent architecture to approximate a linear autoencoder of the input sequences, which can be found with a closed-form solution.

Memorization Permuted-MNIST

Linear Memory Networks

no code implementations8 Nov 2018 Davide Bacciu, Antonio Carta, Alessandro Sperduti

By building on such conceptualization, we introduce the Linear Memory Network, a recurrent model comprising a feedforward neural network, realizing the non-linear functional transformation, and a linear autoencoder for sequences, implementing the memory component.

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