1 code implementation • 10 Nov 2015 • Davide Maltoni, Vincenzo Lomonaco
Recent works demonstrated the usefulness of temporal coherence to regularize supervised training or to learn invariant features with deep architectures.
1 code implementation • 9 May 2017 • Vincenzo Lomonaco, Davide Maltoni
Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem.
1 code implementation • 22 Jun 2018 • Davide Maltoni, Vincenzo Lomonaco
It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge.
1 code implementation • 12 Oct 2018 • Claudia Carpineti, Vincenzo Lomonaco, Luca Bedogni, Marco Di Felice, Luciano Bononi
Making applications aware of the mobility experienced by the user can open the door to a wide range of novel services in different use-cases, from smart parking to vehicular traffic monitoring.
no code implementations • 31 Oct 2018 • Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat, Davide Maltoni
Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills.
no code implementations • 13 Nov 2018 • Vincenzo Lomonaco, Angelo Trotta, Marta Ziosi, Juan de Dios Yáñez Ávila, Natalia Díaz-Rodríguez
In recent years, a rising numbers of people arrived in the European Union, traveling across the Mediterranean Sea or overland through Southeast Europe in what has been later named as the European migrant crisis.
1 code implementation • 24 May 2019 • Vincenzo Lomonaco, Karan Desai, Eugenio Culurciello, Davide Maltoni
High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques.
no code implementations • 29 Jun 2019 • Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat, Natalia Díaz-Rodríguez
An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world.
5 code implementations • 8 Jul 2019 • Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini
Ideally, continual learning should be triggered by the availability of short videos of single objects and performed on-line on on-board hardware with fine-grained updates.
1 code implementation • 9 Sep 2019 • Jary Pomponi, Simone Scardapane, Vincenzo Lomonaco, Aurelio Uncini
Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures.
2 code implementations • 15 Nov 2019 • Qi She, Fan Feng, Xinyue Hao, Qihan Yang, Chuanlin Lan, Vincenzo Lomonaco, Xuesong Shi, Zhengwei Wang, Yao Guo, Yimin Zhang, Fei Qiao, Rosa H. M. Chan
Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks.
3 code implementations • 2 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.
no code implementations • 20 Mar 2020 • German I. Parisi, Vincenzo Lomonaco
Online continual learning (OCL) refers to the ability of a system to learn over time from a continuous stream of data without having to revisit previously encountered training samples.
no code implementations • 26 Apr 2020 • Qi She, Fan Feng, Qi Liu, Rosa H. M. Chan, Xinyue Hao, Chuanlin Lan, Qihan Yang, Vincenzo Lomonaco, German I. Parisi, Heechul Bae, Eoin Brophy, Baoquan Chen, Gabriele Graffieti, Vidit Goel, Hyonyoung Han, Sathursan Kanagarajah, Somesh Kumar, Siew-Kei Lam, Tin Lun Lam, Liang Ma, Davide Maltoni, Lorenzo Pellegrini, Duvindu Piyasena, ShiLiang Pu, Debdoot Sheet, Soonyong Song, Youngsung Son, Zhengwei Wang, Tomas E. Ward, Jianwen Wu, Meiqing Wu, Di Xie, Yangsheng Xu, Lin Yang, Qiaoyong Zhong, Liguang Zhou
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top $8$ finalists (out of over~$150$ teams).
1 code implementation • 14 Sep 2020 • Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni
In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.
no code implementations • 12 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.
2 code implementations • 29 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.
4 code implementations • 1 Apr 2021 • Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, Gido van de Ven, Martin Mundt, Qi She, Keiland Cooper, Jeremy Forest, Eden Belouadah, Simone Calderara, German I. Parisi, Fabio Cuzzolin, Andreas Tolias, Simone Scardapane, Luca Antiga, Subutai Amhad, Adrian Popescu, Christopher Kanan, Joost Van de Weijer, Tinne Tuytelaars, Davide Bacciu, Davide Maltoni
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning.
1 code implementation • 17 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.
1 code implementation • 24 May 2021 • Lorenzo Pellegrini, Vincenzo Lomonaco, Gabriele Graffieti, Davide Maltoni
On-device training for personalized learning is a challenging research problem.
no code implementations • 14 Jul 2021 • Davide Bacciu, Siranush Akarmazyan, Eric Armengaud, Manlio Bacco, George Bravos, Calogero Calandra, Emanuele Carlini, Antonio Carta, Pietro Cassara, Massimo Coppola, Charalampos Davalas, Patrizio Dazzi, Maria Carmela Degennaro, Daniele Di Sarli, Jürgen Dobaj, Claudio Gallicchio, Sylvain Girbal, Alberto Gotta, Riccardo Groppo, Vincenzo Lomonaco, Georg Macher, Daniele Mazzei, Gabriele Mencagli, Dimitrios Michail, Alessio Micheli, Roberta Peroglio, Salvatore Petroni, Rosaria Potenza, Farank Pourdanesh, Christos Sardianos, Konstantinos Tserpes, Fulvio Tagliabò, Jakob Valtl, Iraklis Varlamis, Omar Veledar
This paper discusses the perspective of the H2020 TEACHING project on the next generation of autonomous applications running in a distributed and highly heterogeneous environment comprising both virtual and physical resources spanning the edge-cloud continuum.
no code implementations • 27 Oct 2021 • Ajmal Shahbaz, Salman Khan, Mohammad Asiful Hossain, Vincenzo Lomonaco, Kevin Cannons, Zhan Xu, Fabio Cuzzolin
The aim of this paper is to formalize a new continual semi-supervised learning (CSSL) paradigm, proposed to the attention of the machine learning community via the IJCAI 2021 International Workshop on Continual Semi-Supervised Learning (CSSL-IJCAI), with the aim of raising field awareness about this problem and mobilizing its effort in this direction.
no code implementations • 17 Nov 2021 • Andrea Cossu, Marta Ziosi, Vincenzo Lomonaco
The increasing attention on Artificial Intelligence (AI) regulation has led to the definition of a set of ethical principles grouped into the Sustainable AI framework.
no code implementations • 6 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.
1 code implementation • 13 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.
no code implementations • 3 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.
1 code implementation • 28 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).
no code implementations • 19 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.
no code implementations • 12 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.
1 code implementation • 19 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.
no code implementations • 14 Jun 2022 • Rudy Semola, Vincenzo Lomonaco, Davide Bacciu
The two main future trends for companies that want to build machine learning-based applications and systems are real-time inference and continual updating.
1 code implementation • 29 Jun 2022 • Federico Matteoni, Andrea Cossu, Claudio Gallicchio, Vincenzo Lomonaco, Davide Bacciu
Continual Learning (CL) on time series data represents a promising but under-studied avenue for real-world applications.
1 code implementation • 4 Jul 2022 • Julio Hurtado, Alain Raymond-Saez, Vladimir Araujo, Vincenzo Lomonaco, Alvaro Soto, Davide Bacciu
This paper introduces Memory Outlier Elimination (MOE), a method for identifying and eliminating outliers in the memory buffer by choosing samples from label-homogeneous subpopulations.
1 code implementation • 13 Dec 2022 • Lorenzo Pellegrini, Chenchen Zhu, Fanyi Xiao, Zhicheng Yan, Antonio Carta, Matthias De Lange, Vincenzo Lomonaco, Roshan Sumbaly, Pau Rodriguez, David Vazquez
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community.
no code implementations • 6 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.
1 code implementation • 26 Jan 2023 • Hamed Hemati, Andrea Cossu, Antonio Carta, Julio Hurtado, Lorenzo Pellegrini, Davide Bacciu, Vincenzo Lomonaco, Damian Borth
We propose two stochastic stream generators that produce a wide range of CIR streams starting from a single dataset and a few interpretable control parameters.
no code implementations • 29 Jan 2023 • Julio Hurtado, Dario Salvati, Rudy Semola, Mattia Bosio, Vincenzo Lomonaco
In this work, we present a brief introduction to predictive maintenance, non-stationary environments, and continual learning, together with an extensive review of the current state of applying continual learning in real-world applications and specifically in predictive maintenance.
1 code implementation • 2 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.
1 code implementation • 28 Mar 2023 • Antonio Carta, Andrea Cossu, Vincenzo Lomonaco, Davide Bacciu, Joost Van de Weijer
We formalize this problem as a Distributed Continual Learning scenario, where SCD adapt to local tasks and a CL model consolidates the knowledge from the resulting stream of models without looking at the SCD's private data.
no code implementations • 16 Jun 2023 • Felipe del Rio, Julio Hurtado, Cristian Buc, Alvaro Soto, Vincenzo Lomonaco
One of the objectives of Continual Learning is to learn new concepts continually over a stream of experiences and at the same time avoid catastrophic forgetting.
1 code implementation • 19 Jun 2023 • Hamed Hemati, Vincenzo Lomonaco, Davide Bacciu, Damian Borth
Inspired by latent replay methods in CL, we propose partial weight generation for the final layers of a model using hypernetworks while freezing the initial layers.
1 code implementation • 17 Jul 2023 • Luigi Quarantiello, Simone Marzeddu, Antonio Guzzi, Vincenzo Lomonaco
In the last few decades we have witnessed a significant development in Artificial Intelligence (AI) thanks to the availability of a variety of testbeds, mostly based on simulated environments and video games.
2 code implementations • 20 Aug 2023 • Albin Soutif--Cormerais, Antonio Carta, Andrea Cossu, Julio Hurtado, Hamed Hemati, Vincenzo Lomonaco, Joost Van de Weijer
Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream.
no code implementations • 22 Sep 2023 • Eric Nuertey Coleman, Julio Hurtado, Vincenzo Lomonaco
However, one limitation of this scenario is that users cannot modify the internal knowledge of the model, and the only way to add or modify internal knowledge is by explicitly mentioning it to the model during the current interaction.
no code implementations • 5 Oct 2023 • Dhireesha Kudithipudi, Anurag Daram, Abdullah M. Zyarah, Fatima Tuz Zohora, James B. Aimone, Angel Yanguas-Gil, Nicholas Soures, Emre Neftci, Matthew Mattina, Vincenzo Lomonaco, Clare D. Thiem, Benjamin Epstein
Lifelong learning - an agent's ability to learn throughout its lifetime - is a hallmark of biological learning systems and a central challenge for artificial intelligence (AI).
no code implementations • 20 Nov 2023 • Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost Van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past.
no code implementations • 9 Mar 2024 • Rudy Semola, Julio Hurtado, Vincenzo Lomonaco, Davide Bacciu
This paper aims to explore the role of hyperparameter selection in continual learning and the necessity of continually and automatically tuning them according to the complexity of the task at hand.
1 code implementation • 5 Apr 2024 • Lanpei Li, Enrico Donato, Vincenzo Lomonaco, Egidio Falotico
The framework leverages Policy Distillation (PD) to transfer knowledge from expert policies to a continually evolving student policy network.
2 code implementations • 11 Apr 2024 • Lanpei Li, Elia Piccoli, Andrea Cossu, Davide Bacciu, Vincenzo Lomonaco
Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data.
no code implementations • 7 May 2024 • Hamed Hemati, Lorenzo Pellegrini, Xiaotian Duan, Zixuan Zhao, Fangfang Xia, Marc Masana, Benedikt Tscheschner, Eduardo Veas, Yuxiang Zheng, Shiji Zhao, Shao-Yuan Li, Sheng-Jun Huang, Vincenzo Lomonaco, Gido M. van de Ven
Continual learning (CL) provides a framework for training models in ever-evolving environments.