Here you can find a consolidated (a.k.a. slowly updated) list of my publications. A frequently updated (and possibly noisy) list of works is available on my Google Scholar profile.
Please find below a short list of highlight publications for my recent activity.
Caro, Valerio De; Bacciu, Davide; Gallicchio, Claudio Decentralized Plasticity in Reservoir Dynamical Networks for Pervasive Environments Workshop Proceedings of the 2023 ICML Workshop on Localized Learning: Decentralized Model Updates via Non-Global Objectives
, 2023. Caro, Valerio De; Gallicchio, Claudio; Bacciu, Davide Federated Adaptation of Reservoirs via Intrinsic Plasticity Conference Proceedings of the 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2022), 2022. Ferrari, Elisa; Gargani, Luna; Barbieri, Greta; Ghiadoni, Lorenzo; Faita, Francesco; Bacciu, Davide A causal learning framework for the analysis and interpretation of COVID-19 clinical data Journal Article In: Plos One, vol. 17, no. 5, 2022. Crecchi, Francesco; de Bodt, Cyril; Bacciu, Davide; Verleysen, Michel; John, Lee Perplexity-free Parametric t-SNE Conference Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20), 2020. Davide, Bacciu; Daniele, Castellana Bayesian Mixtures of Hidden Tree Markov Models for Structured Data Clustering Journal Article In: Neurocomputing, vol. 342, pp. 49-59, 2019, ISBN: 0925-2312. Davide, Bacciu; Daniele, Castellana Mixture of Hidden Markov Models as Tree Encoder Conference Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'18), i6doc.com, Louvain-la-Neuve, Belgium, 2018, ISBN: 978-287587047-6. Davide, Bacciu An Iterative Feature Filter for Sensor Timeseries in Pervasive Computing Applications Conference Communications in Computer and Information Science - Engineering Applications of Neural Networks, vol. 459, Springer International Publishing, 2014. H, Jarman Ian; A, Etchells Terence; Davide, Bacciu; M, Garibaldi John; O, Ellis Ian; JG, Lisboa Paulo Clustering of protein expression data: a benchmark of statistical and neural approaches Journal Article In: Soft Computing-A Fusion of Foundations, Methodologies and Applications, vol. 15, no. 8, pp. 1459–1469, 2011, ISSN: 1432-7643. Davide, Bacciu; Alessio, Micheli; Alessandro, Sperduti Compositional Generative Mapping of Structured Data Conference Proceedings of the 2010 IEEE InternationalJoint Conference on Neural Networks(IJCNN'10), IEEE, 2010. S, Fernandes Ana; Davide, Bacciu; H, Jarman Ian; A, Etchells Terence; M, Fonseca Jose; JG, Lisboa Paulo Different Methodologies for Patient Stratification Using Survival Data Conference Lecture Notes in Computer ScienceComputational Intelligence Methods for Bioinformatics and Biostatistics, vol. 6160, 2010. Davide, Bacciu; Antonina, Starita Expansive competitive learning for kernel vector quantization Journal Article In: Pattern Recognition Letters, vol. 30, no. 6, pp. 641–651, 2009, ISSN: 0167-8655. JG, Lisboa Paulo; H, Jarman Ian; A, Etchells Terence; Davide, Bacciu; M, Garibaldi John Model-based and model-free clustering: a case study of protein expression data for breast cancer Conference PROCEEDINGS OF THE 2009 UK WORKSHOP ON COMPUTATIONAL INTELLIGENCE, 2009. Davide, Bacciu; H, Jarman Ian; A, Etchells Terence; G, Lisboa Paulo J Patient stratification with competing risks by multivariate Fisher distance Conference 2009 International Joint Conference on Neural Networks, IEEE, 2009. Davide, Bacciu; Antonina, Starita Competitive Repetition Suppression (CoRe) Clustering: A Biologically Inspired Learning Model With Application to Robust Clustering Journal Article In: Neural Networks, IEEE Transactions on, vol. 19, no. 11, pp. 1922 -1941, 2008, ISSN: 1045-9227. Davide, Bacciu A Perceptual Learning Model to Discover the Hierarchical Latent Structure of Image Collections PhD Thesis 2008. Davide, BACCIU; Elia, BIGANZOLI; JG, LISBOA Paulo; Antonina, Starita Are Model-based Clustering and Neural Clustering Consistent? A Case Study from Bioinformatics Conference Proceedings of the 12th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES'08), vol. 5178, Springer, 2008. Davide, Bacciu; Antonina, Starita Convergence Behavior of Competitive Repetition-Suppression Clustering Conference Neural Information Processing, Lecture Notes in Computer Science, vol. 4984, Springer, 2008. Davide, Bacciu; Antonina, Starita A Robust Bio-Inspired Clustering Algorithm for the Automatic Determination of Unknown Cluster Number Conference 2007 International Joint Conference on Neural Networks, IEEE, 2007. Davide, Bacciu; Antonina, Starita Competitive Repetition-suppression (CoRe) Learning Conference ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 1, Lecture Notes in Computer Science, vol. 4131, Springer Verlag, 2006.@workshop{nokey,
title = {Decentralized Plasticity in Reservoir Dynamical Networks for Pervasive Environments},
author = {Valerio De Caro and Davide Bacciu and Claudio Gallicchio
},
url = {https://openreview.net/forum?id=5hScPOeDaR, PDF},
year = {2023},
date = {2023-07-29},
urldate = {2023-07-29},
booktitle = {Proceedings of the 2023 ICML Workshop on Localized Learning: Decentralized Model Updates via Non-Global Objectives
},
keywords = {},
pubstate = {published},
tppubtype = {workshop}
}
@conference{Caro2022,
title = {Federated Adaptation of Reservoirs via Intrinsic Plasticity},
author = {Valerio {De Caro} and Claudio Gallicchio and Davide Bacciu},
editor = {Michel Verleysen},
url = {https://arxiv.org/abs/2206.11087, Arxiv},
year = {2022},
date = {2022-10-05},
urldate = {2022-10-05},
booktitle = {Proceedings of the 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2022)},
abstract = {We propose a novel algorithm for performing federated learning with Echo State Networks (ESNs) in a client-server scenario. In particular, our proposal focuses on the adaptation of reservoirs by combining Intrinsic Plasticity with Federated Averaging. The former is a gradient-based method for adapting the reservoir's non-linearity in a local and unsupervised manner, while the latter provides the framework for learning in the federated scenario. We evaluate our approach on real-world datasets from human monitoring, in comparison with the previous approach for federated ESNs existing in literature. Results show that adapting the reservoir with our algorithm provides a significant improvement on the performance of the global model. },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{DBLP:journals/corr/abs-2105-06998,
title = {A causal learning framework for the analysis and interpretation of COVID-19 clinical data},
author = {Elisa Ferrari and Luna Gargani and Greta Barbieri and Lorenzo Ghiadoni and Francesco Faita and Davide Bacciu},
url = {https://arxiv.org/abs/2105.06998, Arxiv},
doi = {doi.org/10.1371/journal.pone.0268327},
year = {2022},
date = {2022-05-19},
urldate = {2022-05-19},
journal = {Plos One},
volume = {17},
number = {5},
abstract = {We present a workflow for clinical data analysis that relies on Bayesian Structure Learning (BSL), an unsupervised learning approach, robust to noise and biases, that allows to incorporate prior medical knowledge into the learning process and that provides explainable results in the form of a graph showing the causal connections among the analyzed features. The workflow consists in a multi-step approach that goes from identifying the main causes of patient's outcome through BSL, to the realization of a tool suitable for clinical practice, based on a Binary Decision Tree (BDT), to recognize patients at high-risk with information available already at hospital admission time. We evaluate our approach on a feature-rich COVID-19 dataset, showing that the proposed framework provides a schematic overview of the multi-factorial processes that jointly contribute to the outcome. We discuss how these computational findings are confirmed by current understanding of the COVID-19 pathogenesis. Further, our approach yields to a highly interpretable tool correctly predicting the outcome of 85% of subjects based exclusively on 3 features: age, a previous history of chronic obstructive pulmonary disease and the PaO2/FiO2 ratio at the time of arrival to the hospital. The inclusion of additional information from 4 routine blood tests (Creatinine, Glucose, pO2 and Sodium) increases predictive accuracy to 94.5%. },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{esann20Crecchi,
title = { Perplexity-free Parametric t-SNE},
author = {Francesco Crecchi and Cyril de Bodt and Davide Bacciu and Michel Verleysen and Lee John},
editor = {Michel Verleysen},
year = {2020},
date = {2020-04-21},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'20)},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{neucomBayesHTMM,
title = {Bayesian Mixtures of Hidden Tree Markov Models for Structured Data Clustering},
author = {Bacciu Davide and Castellana Daniele},
url = {https://doi.org/10.1016/j.neucom.2018.11.091},
doi = {10.1016/j.neucom.2018.11.091},
isbn = {0925-2312},
year = {2019},
date = {2019-05-21},
journal = {Neurocomputing},
volume = {342},
pages = {49-59},
abstract = {The paper deals with the problem of unsupervised learning with structured data, proposing a mixture model approach to cluster tree samples. First, we discuss how to use the Switching-Parent Hidden Tree Markov Model, a compositional model for learning tree distributions, to define a finite mixture model where the number of components is fixed by a hyperparameter. Then, we show how to relax such an assumption by introducing a Bayesian non-parametric mixture model where the number of necessary hidden tree components is learned from data. Experimental validation on synthetic and real datasets show the benefit of mixture models over simple hidden tree models in clustering applications. Further, we provide a characterization of the behaviour of the two mixture models for different choices of their hyperparameters.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{esann2018Tree,
title = {Mixture of Hidden Markov Models as Tree Encoder},
author = {Bacciu Davide and Castellana Daniele},
editor = {Michel Verleysen},
isbn = {978-287587047-6},
year = {2018},
date = {2018-04-26},
urldate = {2018-04-26},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN'18)},
pages = {543-548},
publisher = {i6doc.com},
address = {Louvain-la-Neuve, Belgium},
abstract = {The paper introduces a new probabilistic tree encoder based on a mixture of Bottom-up Hidden Tree Markov Models. The ability to recognise similar structures in data is experimentally assessed both in clusterization and classification tasks. The results of these preliminary experiments suggest that the model can be successfully used to compress the tree structural and label patterns in a vectorial representation.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{icfEann14,
title = {An Iterative Feature Filter for Sensor Timeseries in Pervasive Computing Applications},
author = {Bacciu Davide},
doi = {10.1007/978-3-319-11071-4_4},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {Communications in Computer and Information Science - Engineering Applications of Neural Networks},
journal = {COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE},
volume = {459},
pages = {39--48},
publisher = {Springer International Publishing},
abstract = {The paper discusses an efficient feature selection approach for multivariate timeseries of heterogeneous sensor data within a pervasive computing scenario. An iterative filtering procedure is devised
to reduce information redundancy measured in terms of timeseries cross-correlation. The algorithm is capable of identifying non-redundant sensor sources in an unsupervised fashion even in presence of a large proportion of noisy features. A comparative experimental analysis on real-world data
from pervasive computing applications is provided, showing that the algorithm addresses major limitations of unsupervised filters in literature when dealing with sensor timeseries.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
to reduce information redundancy measured in terms of timeseries cross-correlation. The algorithm is capable of identifying non-redundant sensor sources in an unsupervised fashion even in presence of a large proportion of noisy features. A comparative experimental analysis on real-world data
from pervasive computing applications is provided, showing that the algorithm addresses major limitations of unsupervised filters in literature when dealing with sensor timeseries.@article{soco2011,
title = {Clustering of protein expression data: a benchmark of statistical and neural approaches},
author = {Jarman Ian H and Etchells Terence A and Bacciu Davide and Garibaldi John M and Ellis Ian O and Lisboa Paulo JG},
url = {http://dx.doi.org/10.1007/s00500-010-0596-9},
doi = {10.1007/s00500-010-0596-9},
issn = {1432-7643},
year = {2011},
date = {2011-01-01},
journal = {Soft Computing-A Fusion of Foundations, Methodologies and Applications},
volume = {15},
number = {8},
pages = {1459--1469},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{11568_136433,
title = {Compositional Generative Mapping of Structured Data},
author = {Bacciu Davide and Micheli Alessio and Sperduti Alessandro},
doi = {10.1109/IJCNN.2010.5596606},
year = {2010},
date = {2010-01-01},
urldate = {2010-01-01},
booktitle = {Proceedings of the 2010 IEEE InternationalJoint Conference on Neural Networks(IJCNN'10)},
pages = {1359--1366},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{11568_465483,
title = {Different Methodologies for Patient Stratification Using Survival Data},
author = {Fernandes Ana S and Bacciu Davide and Jarman Ian H and Etchells Terence A and Fonseca Jose M and Lisboa Paulo JG},
doi = {10.1007/978-3-642-14571-1_21},
year = {2010},
date = {2010-01-01},
booktitle = {Lecture Notes in Computer ScienceComputational Intelligence Methods for Bioinformatics and Biostatistics},
journal = {LECTURE NOTES IN COMPUTER SCIENCE},
volume = {6160},
pages = {276--290},
abstract = {Clinical characterization of breast cancer patients related to their risk and profiles is an important part for making their correct prognostic assessments. This paper first proposes a prognostic index obtained when it is applied a flexible non-linear time-to-event model and compares it to a widely used linear survival estimator. This index underpins different stratification methodologies including informed clustering utilising the principle of learning metrics, regression trees and recursive application of the log-rank test. Missing data issue was overcome using multiple imputation, which was applied to a neural network model of survival fitted to a data set for breast cancer (n=743). It was found the three methodologies broadly agree, having however important differences.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{patrec2009,
title = {Expansive competitive learning for kernel vector quantization},
author = {Bacciu Davide and Starita Antonina},
url = {http://dx.doi.org/10.1016/j.patrec.2009.01.002},
doi = {10.1016/j.patrec.2009.01.002},
issn = {0167-8655},
year = {2009},
date = {2009-01-01},
journal = {Pattern Recognition Letters},
volume = {30},
number = {6},
pages = {641--651},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{11568_466869,
title = {Model-based and model-free clustering: a case study of protein expression data for breast cancer},
author = {Lisboa Paulo JG and Jarman Ian H and Etchells Terence A and Bacciu Davide and Garibaldi John M},
year = {2009},
date = {2009-01-01},
booktitle = {PROCEEDINGS OF THE 2009 UK WORKSHOP ON COMPUTATIONAL INTELLIGENCE},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{11568_465484,
title = {Patient stratification with competing risks by multivariate Fisher distance},
author = {Bacciu Davide and Jarman Ian H and Etchells Terence A and Lisboa Paulo J G},
doi = {10.1109/IJCNN.2009.5179077},
year = {2009},
date = {2009-01-01},
urldate = {2009-01-01},
booktitle = {2009 International Joint Conference on Neural Networks},
pages = {3453--3460},
publisher = {IEEE},
abstract = {Early characterization of patients with respect to their predicted response to treatment is a fundamental step towards the delivery of effective, personalized care. Starting from the results of a time-to-event model with competing risks using the framework of partial logistic artificial neural networks with automatic relevance determination (PLANNCR-ARD), we discuss an effective semi-supervised approach to patient stratification with application to Acute Myeloid Leukaemia (AML) data (n = 509) acquired prospectively by the GIMEMA consortium. Multiple prognostic indices provided by the survival model are exploited to build a metric based on the Fisher information matrix. Cluster number estimation is then performed in the Fisher-induced affine space, yielding to the discovery of a stratification of the patients into groups characterized by significantly different mortality risks following induction therapy in AML. The proposed model is shown to be able to cluster the input data, while promoting specificity of both target outcomes, namely Complete Remission (CR) and Induction Death (ID). This generic clustering methodology generates an affine transformation of the data space that is coherent with the prognostic information predicted by the PLANNCR-ARD model.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{coreTNN2008,
title = {Competitive Repetition Suppression (CoRe) Clustering: A Biologically Inspired Learning Model With Application to Robust Clustering},
author = {Bacciu Davide and Starita Antonina},
url = {http://dx.doi.org/10.1016/j.patrec.2009.01.002},
doi = {10.1109/TNN.2008.2004407},
issn = {1045-9227},
year = {2008},
date = {2008-11-01},
urldate = {2008-11-01},
journal = {Neural Networks, IEEE Transactions on},
volume = {19},
number = {11},
pages = {1922 -1941},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@phdthesis{11568_466874,
title = {A Perceptual Learning Model to Discover the Hierarchical Latent Structure of Image Collections},
author = { Bacciu Davide},
url = {http://e-theses.imtlucca.it/id/eprint/7},
doi = {10.6092/imtlucca/e-theses/7},
year = {2008},
date = {2008-01-01},
urldate = {2008-01-01},
publisher = {IMT Lucca},
abstract = {Biology has been an unparalleled source of inspiration for the work of researchers in several scientific and engineering fields including computer vision. The starting point of this thesis is the neurophysiological properties of the human early visual system, in particular, the cortical mechanism that mediates learning by exploiting information about stimuli repetition. Repetition has long been considered a fundamental correlate of skill acquisition andmemory formation in biological aswell as computational learning models. However, recent studies have shown that biological neural networks have differentways of exploiting repetition in forming memory maps. The thesis focuses on a perceptual learning mechanism called repetition suppression, which exploits the temporal distribution of neural activations to drive an efficient neural allocation for a set of stimuli. This explores the neurophysiological hypothesis that repetition suppression serves as an unsupervised perceptual learning mechanism that can drive efficient memory formation by reducing the overall size of stimuli representation while strengthening the responses of the most selective neurons. This interpretation of repetition is different from its traditional role in computational learning models mainly to induce convergence and reach training stability, without using this information to provide focus for the neural representations of the data. The first part of the thesis introduces a novel computational model with repetition suppression, which forms an unsupervised competitive systemtermed CoRe, for Competitive Repetition-suppression learning. The model is applied to generalproblems in the fields of computational intelligence and machine learning. Particular emphasis is placed on validating the model as an effective tool for the unsupervised exploration of bio-medical data. In particular, it is shown that the repetition suppression mechanism efficiently addresses the issues of automatically estimating the number of clusters within the data, as well as filtering noise and irrelevant input components in highly dimensional data, e.g. gene expression levels from DNA Microarrays. The CoRe model produces relevance estimates for the each covariate which is useful, for instance, to discover the best discriminating bio-markers. The description of the model includes a theoretical analysis using Huber’s robust statistics to show that the model is robust to outliers and noise in the data. The convergence properties of themodel also studied. It is shown that, besides its biological underpinning, the CoRe model has useful properties in terms of asymptotic behavior. By exploiting a kernel-based formulation for the CoRe learning error, a theoretically sound motivation is provided for the model’s ability to avoid local minima of its loss function. To do this a necessary and sufficient condition for global error minimization in vector quantization is generalized by extending it to distance metrics in generic Hilbert spaces. This leads to the derivation of a family of kernel-based algorithms that address the local minima issue of unsupervised vector quantization in a principled way. The experimental results show that the algorithm can achieve a consistent performance gain compared with state-of-the-art learning vector quantizers, while retaining a lower computational complexity (linear with respect to the dataset size). Bridging the gap between the low level representation of the visual content and the underlying high-level semantics is a major research issue of current interest. The second part of the thesis focuses on this problem by introducing a hierarchical and multi-resolution approach to visual content understanding. On a spatial level, CoRe learning is used to pool together the local visual patches by organizing them into perceptually meaningful intermediate structures. On the semantical level, it provides an extension of the probabilistic Latent Semantic Analysis (pLSA) model that allows discovery and organization of the visual topics into a hierarchy of aspects. The proposed hierarchical pLSA model is shown to effectively address the unsupervised discovery of relevant visual classes from pictorial collections, at the same time learning to segment the image regions containing the discovered classes. Furthermore, by drawing on a recent pLSA-based image annotation system, the hierarchical pLSA model is extended to process and representmulti-modal collections comprising textual and visual data. The results of the experimental evaluation show that the proposed model learns to attach textual labels (available only at the level of the whole image) to the discovered image regions, while increasing the precision/ recall performance with respect to flat, pLSA annotation model.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
@conference{11568_465487,
title = {Are Model-based Clustering and Neural Clustering Consistent? A Case Study from Bioinformatics},
author = {BACCIU Davide and BIGANZOLI Elia and LISBOA Paulo JG and Starita Antonina},
doi = {10.1007/978-3-540-85565-1-23},
year = {2008},
date = {2008-01-01},
booktitle = {Proceedings of the 12th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES'08)},
journal = {LECTURE NOTES IN COMPUTER SCIENCE},
volume = {5178},
pages = {181--188},
publisher = {Springer},
abstract = {A novel neural network clustering algorithm, CoRe, is benchmarked against previously published results on a breast cancer data set and applying the method of Partition Around Medoids (PAM). The data serve to compare the samples partitions obtained with the neural network, PAM and model-based algorithms, namely Gaussian Mixture Model (GMM), Variational Bayesian Gaussian Mixture (VBG) and Variational Bayesian Mixtures with Splitting (VBS). It is found that CoRe, on the one hand, agrees with the previously published partitions; on the other hand, it supports the existence of a supplementary cluster that we hypothesize to be an additional tumor subgroup with respect to those previously identified by PAM},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{11568_466667,
title = {Convergence Behavior of Competitive Repetition-Suppression Clustering},
author = {Bacciu Davide and Starita Antonina },
doi = {10.1007/978-3-540-69158-7_52},
year = {2008},
date = {2008-01-01},
booktitle = {Neural Information Processing, Lecture Notes in Computer Science},
volume = {4984},
pages = {497--506},
publisher = {Springer},
abstract = {Competitive Repetition-suppression (CoRe) clustering is a bio-inspired learning algorithm that is capable of automatically determining the unknown cluster number from the data. In a previous work it has been shown how CoRe clustering represents a robust generalization of rival penalized competitive learning (RPCL) by means of M-estimators. This paper studies the convergence behavior of the CoRe model, based on the analysis proposed for the distance-sensitive RPCL (DSRPCL) algorithm. Furthermore, it is proposed a global minimum criterion for learning vector quantization in kernel space that is used to assess the correct location property for the CoRe algorithm.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{11568_466670,
title = {A Robust Bio-Inspired Clustering Algorithm for the Automatic Determination of Unknown Cluster Number},
author = {Bacciu Davide and Starita Antonina },
doi = {10.1109/IJCNN.2007.4371148},
year = {2007},
date = {2007-01-01},
urldate = {2007-01-01},
booktitle = {2007 International Joint Conference on Neural Networks},
pages = {1314--1319},
publisher = {IEEE},
abstract = {The paper introduces a robust clustering algorithm that can automatically determine the unknown cluster number from noisy data without any a-priori information. We show how our clustering algorithm can be derived from a general learning theory, named CoRe learning, that models a cortical memory mechanism called repetition suppression. Moreover, we describe CoRe clustering relationships with Rival Penalized Competitive Learning (RPCL), showing how CoRe extends this model by strengthening the rival penalization estimation by means of robust loss functions. Finally, we present the results of simulations concerning the unsupervised segmentation of noisy images.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{11568_466676,
title = {Competitive Repetition-suppression (CoRe) Learning},
author = {Bacciu Davide and Starita Antonina },
doi = {10.1007/11840817_14},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
booktitle = {ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 1, Lecture Notes in Computer Science},
journal = {LECTURE NOTES IN COMPUTER SCIENCE},
volume = {4131},
pages = {130--139},
publisher = {Springer Verlag},
abstract = {The paper introduces Competitive Repetition-suppression (CoRe) learning, a novel paradigm inspired by a cortical mechanism of perceptual learning called repetition suppression. CoRe learning is an unsupervised, soft-competitive [1] model with conscience [2] that can be used for self-generating compact neural representations of the input stimuli. The key idea underlying the development of CoRe learning is to exploit the temporal distribution of neurons activations as a source of training information and to drive memory formation. As a case study, the paper reports the CoRe learning rules that have been derived for the unsupervised training of a Radial Basis Function network.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}