{"id":1388,"date":"2024-01-01T20:39:37","date_gmt":"2024-01-01T19:39:37","guid":{"rendered":"http:\/\/pages.di.unipi.it\/bacciu\/?page_id=1388"},"modified":"2024-01-03T13:48:48","modified_gmt":"2024-01-03T12:48:48","slug":"other","status":"publish","type":"page","link":"https:\/\/pages.di.unipi.it\/bacciu\/publications\/other\/","title":{"rendered":"Other"},"content":{"rendered":"\n<p><code><div class=\"teachpress_pub_list\"><form name=\"tppublistform\" method=\"get\"><a name=\"tppubs\" id=\"tppubs\"><\/a><\/form><div class=\"teachpress_publication_list\"><h3 class=\"tp_h3\" id=\"tp_h3_2021\">2021<\/h3><div class=\"tp_publication tp_publication_periodical\"><div class=\"tp_pub_number\">1.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Schoitsch, Erwin;  Mylonas, Georgios (Ed.)<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('187','tp_links')\" style=\"cursor:pointer;\">Supporting Privacy Preservation by Distributed and Federated Learning on the Edge<\/a> <span class=\"tp_pub_type periodical\">Periodical<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_issuetitle\">ERCIM News, <\/span><span class=\"tp_pub_additional_volume\">vol. 127, <\/span><span class=\"tp_pub_additional_year\">2021<\/span><span class=\"tp_pub_additional_urldate\">, visited: 30.09.2021<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_187\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('187','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_187\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('187','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_187\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@periodical{Bacciu2021e,<br \/>\r\ntitle = {Supporting Privacy Preservation by Distributed and Federated Learning on the Edge},<br \/>\r\nauthor = { Davide Bacciu and Patrizio Dazzi and Alberto Gotta},<br \/>\r\neditor = {Erwin Schoitsch and Georgios Mylonas},<br \/>\r\nurl = {https:\/\/ercim-news.ercim.eu\/en127\/r-i\/supporting-privacy-preservation-by-distributed-and-federated-learning-on-the-edge},<br \/>\r\nyear  = {2021},<br \/>\r\ndate = {2021-09-30},<br \/>\r\nurldate = {2021-09-30},<br \/>\r\nissuetitle = {ERCIM News},<br \/>\r\nvolume = {127},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {periodical}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('187','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_187\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/ercim-news.ercim.eu\/en127\/r-i\/supporting-privacy-preservation-by-distributed-and-federated-learning-on-the-edge\" title=\"https:\/\/ercim-news.ercim.eu\/en127\/r-i\/supporting-privacy-preservation-by-distrib[...]\" target=\"_blank\">https:\/\/ercim-news.ercim.eu\/en127\/r-i\/supporting-privacy-preservation-by-distrib[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('187','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Supporting Privacy Preservation by Distributed and Federated Learning on the Edge\" src=\"https:\/\/www.ercim.eu\/publication\/logos\/logo300x235.png\" width=\"80\" alt=\"Supporting Privacy Preservation by Distributed and Federated Learning on the Edge\" \/><\/div><\/div><div class=\"tp_publication tp_publication_unpublished\"><div class=\"tp_pub_number\">2.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Ferrari, Elisa;  Bacciu, Davide<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('191','tp_links')\" style=\"cursor:pointer;\">Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss<\/a> <span class=\"tp_pub_type unpublished\">Unpublished<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_howpublished\">Online on Arxiv, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_abstract_link\"><a id=\"tp_abstract_sh_191\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('191','tp_abstract')\" title=\"Show abstract\" style=\"cursor:pointer;\">Abstract<\/a><\/span> | <span class=\"tp_resource_link\"><a id=\"tp_links_sh_191\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('191','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_191\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('191','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_191\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@unpublished{Ferrari2021,<br \/>\r\ntitle = {Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss},<br \/>\r\nauthor = {Elisa Ferrari and Davide Bacciu},<br \/>\r\nurl = {https:\/\/arxiv.org\/abs\/2105.06345, Arxiv},<br \/>\r\nyear  = {2021},<br \/>\r\ndate = {2021-05-13},<br \/>\r\nurldate = {2021-05-13},<br \/>\r\nabstract = {Resilience to class imbalance and confounding biases, together with the assurance of fairness guarantees are highly desirable properties of autonomous decision-making systems with real-life impact. Many different targeted solutions have been proposed to address separately these three problems, however a unifying perspective seems to be missing. With this work, we provide a general formalization, showing that they are different expressions of unbalance. Following this intuition, we formulate a unified loss correction to address issues related to Fairness, Biases and Imbalances (FBI-loss). The correction capabilities of the proposed approach are assessed on three real-world benchmarks, each associated to one of the issues under consideration, and on a family of synthetic data in order to better investigate the effectiveness of our loss on tasks with different complexities. The empirical results highlight that the flexible formulation of the FBI-loss leads also to competitive performances with respect to literature solutions specialised for the single problems.},<br \/>\r\nhowpublished = {Online on Arxiv},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {unpublished}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('191','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_abstract\" id=\"tp_abstract_191\" style=\"display:none;\"><div class=\"tp_abstract_entry\">Resilience to class imbalance and confounding biases, together with the assurance of fairness guarantees are highly desirable properties of autonomous decision-making systems with real-life impact. Many different targeted solutions have been proposed to address separately these three problems, however a unifying perspective seems to be missing. With this work, we provide a general formalization, showing that they are different expressions of unbalance. Following this intuition, we formulate a unified loss correction to address issues related to Fairness, Biases and Imbalances (FBI-loss). The correction capabilities of the proposed approach are assessed on three real-world benchmarks, each associated to one of the issues under consideration, and on a family of synthetic data in order to better investigate the effectiveness of our loss on tasks with different complexities. The empirical results highlight that the flexible formulation of the FBI-loss leads also to competitive performances with respect to literature solutions specialised for the single problems.<\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('191','tp_abstract')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_191\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"ai ai-arxiv\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/arxiv.org\/abs\/2105.06345\" title=\"Arxiv\" target=\"_blank\">Arxiv<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('191','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss\" src=\"http:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2024\/01\/arxiv.png\" width=\"80\" alt=\"Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss\" \/><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2019\">2019<\/h3><div class=\"tp_publication tp_publication_online\"><div class=\"tp_pub_number\">3.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Bacciu, Davide<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('138','tp_links')\" style=\"cursor:pointer;\">Reti neurali e linguaggio. Le insidie nascoste di un'algebra delle parole<\/a> <span class=\"tp_pub_type online\">Online<\/span> <\/p><p class=\"tp_pub_additional\"> Tavosanis, Mirko (Ed.): <span class=\"tp_pub_additional_organization\">Lingua Italiana - Treccani <\/span><span class=\"tp_pub_additional_year\">2019<\/span><span class=\"tp_pub_additional_urldate\">, visited: 03.12.2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_138\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('138','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_138\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('138','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_138\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@online{treccani19,<br \/>\r\ntitle = {Reti neurali e linguaggio. Le insidie nascoste di un'algebra delle parole},<br \/>\r\nauthor = {Davide Bacciu},<br \/>\r\neditor = {Mirko Tavosanis},<br \/>\r\nurl = {http:\/\/www.treccani.it\/magazine\/lingua_italiana\/speciali\/IA\/02_Bacciu.html},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-12-03},<br \/>\r\nurldate = {2019-12-03},<br \/>\r\norganization = {Lingua Italiana - Treccani},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {online}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('138','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_138\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/www.treccani.it\/magazine\/lingua_italiana\/speciali\/IA\/02_Bacciu.html\" title=\"http:\/\/www.treccani.it\/magazine\/lingua_italiana\/speciali\/IA\/02_Bacciu.html\" target=\"_blank\">http:\/\/www.treccani.it\/magazine\/lingua_italiana\/speciali\/IA\/02_Bacciu.html<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('138','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Reti neurali e linguaggio. Le insidie nascoste di un'algebra delle parole\" src=\"http:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2024\/01\/Logo-Vettoriale-Treccani-Verticale.jpg\" width=\"80\" alt=\"Reti neurali e linguaggio. Le insidie nascoste di un'algebra delle parole\" \/><\/div><\/div><div class=\"tp_publication tp_publication_presentation\"><div class=\"tp_pub_number\">4.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Cosimo, Della Santina;  Giuseppe, Averta;  Visar, Arapi;  Alessandro, Settimi;  Giuseppe, Catalano Manuel;  Davide, Bacciu;  Antonio, Bicchi;  Matteo, Bianchi<\/p><p class=\"tp_pub_title\">Autonomous Grasping with SoftHands: Combining Human Inspiration, Deep Learning and Embodied Machine Intelligence <span class=\"tp_pub_type presentation\">Presentation<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_date\">11.09.2019<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_133\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('133','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_133\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@misc{automatica2019,<br \/>\r\ntitle = {Autonomous Grasping with SoftHands: Combining Human Inspiration, Deep Learning and Embodied Machine Intelligence},<br \/>\r\nauthor = {Della Santina Cosimo and Averta Giuseppe and Arapi Visar and Settimi Alessandro and Catalano Manuel Giuseppe and Bacciu Davide and Bicchi Antonio and Bianchi Matteo},<br \/>\r\nyear  = {2019},<br \/>\r\ndate = {2019-09-11},<br \/>\r\nbooktitle = {Oral contribution to AUTOMATICA.IT 2019 },<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {presentation}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('133','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2016\">2016<\/h3><div class=\"tp_publication tp_publication_online\"><div class=\"tp_pub_number\">5.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Davide, Bacciu;  Antonio, Carta;  Stefania, Gnesi;  Laura, Semini<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('101','tp_links')\" style=\"cursor:pointer;\">Adopting a Machine Learning Approach in the Design of Smart Transportation Systems<\/a> <span class=\"tp_pub_type online\">Online<\/span> <\/p><p class=\"tp_pub_additional\">van der Me, Rob;  Shashaj, Ariona (Ed.): <span class=\"tp_pub_additional_organization\">ERCIM News Magazine <\/span><span class=\"tp_pub_additional_year\">2016<\/span><span class=\"tp_pub_additional_urldate\">, visited: 01.04.2016<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_101\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('101','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_101\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('101','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_101\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@online{ercim2016,<br \/>\r\ntitle = {Adopting a Machine Learning Approach in the Design of Smart Transportation Systems},<br \/>\r\nauthor = {Bacciu Davide and Carta Antonio and Gnesi Stefania and Semini Laura },<br \/>\r\neditor = {Rob van der Me and Ariona Shashaj},<br \/>\r\nurl = {http:\/\/ercim-news.ercim.eu\/en105\/special\/adopting-a-machine-learning-approach-in-the-design-of-smart-transportation-systems},<br \/>\r\nissn = {0926-4981 },<br \/>\r\nyear  = {2016},<br \/>\r\ndate = {2016-04-01},<br \/>\r\nurldate = {2016-04-01},<br \/>\r\norganization = {ERCIM News Magazine},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {online}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('101','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_101\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/ercim-news.ercim.eu\/en105\/special\/adopting-a-machine-learning-approach-in-the-design-of-smart-transportation-systems\" title=\"http:\/\/ercim-news.ercim.eu\/en105\/special\/adopting-a-machine-learning-approach-in[...]\" target=\"_blank\">http:\/\/ercim-news.ercim.eu\/en105\/special\/adopting-a-machine-learning-approach-in[...]<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('101','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Adopting a Machine Learning Approach in the Design of Smart Transportation Systems\" src=\"https:\/\/www.ercim.eu\/publication\/logos\/logo300x235.png\" width=\"80\" alt=\"Adopting a Machine Learning Approach in the Design of Smart Transportation Systems\" \/><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2015\">2015<\/h3><div class=\"tp_publication tp_publication_presentation\"><div class=\"tp_pub_number\">6.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Oberdan, Parodi;  Federico, Vozzi;  Erina, Ferro;  Luigi, Fortunati;  Alessio, Micheli;  Claudio, Gallicchio;  Davide, Bacciu;  Stefano, Chessa;  Antonio, Ascolese<\/p><p class=\"tp_pub_title\">Preventing cognitive decline, sedentariness and malnutrition: the DOREMI approach <span class=\"tp_pub_type presentation\">Presentation<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_date\">29.10.2015<\/span><span class=\"tp_pub_additional_note\">, (Palermo, October 29-30, 2015)<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_103\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('103','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_103\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@misc{icities2015,<br \/>\r\ntitle = {Preventing cognitive decline, sedentariness and malnutrition: the DOREMI approach},<br \/>\r\nauthor = {Parodi Oberdan and Vozzi Federico and Ferro Erina and Fortunati Luigi and Micheli Alessio and Gallicchio Claudio and Bacciu Davide and Chessa Stefano and Ascolese Antonio},<br \/>\r\nyear  = {2015},<br \/>\r\ndate = {2015-10-29},<br \/>\r\nbooktitle = {The CINI Annual Workshop on ICT for Smart Cities and Communities (I-CiTies 2015)},<br \/>\r\nnote = {Palermo, October 29-30, 2015},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {presentation}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('103','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2012\">2012<\/h3><div class=\"tp_publication tp_publication_presentation\"><div class=\"tp_pub_number\">7.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Same, Abdel-Naby;  Giuseppe, Amato;  Davide, Bacciu;  Mathias, Broxvall;  Stefano, Chessa;  Sonya, Coleman;  Maurizio, Di Rocco;  Mauro, Dragone;  Claudio, Gallicchio;  Claudio, Gennaro;  Roberto, Guzman;  Raul, Lopez;  Hector, Lozano;  Liam, Maguire;  Martin, McGinnity T;  Alessio, Micheli;  MP, O'Hare Greg;  Federico, Pecora;  AK, Ray;  Arantxa, Renteria;  Alessandro, Saffiotti;  David, Swords;  Claudio, Vairo<\/p><p class=\"tp_pub_title\">Robotic UBIquitous COgnitive Networks <span class=\"tp_pub_type presentation\">Presentation<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_date\">01.01.2012<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_29\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('29','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_29\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@misc{11568_466873,<br \/>\r\ntitle = {Robotic UBIquitous COgnitive Networks},<br \/>\r\nauthor = {Abdel-Naby Same and Amato Giuseppe and Bacciu Davide and Broxvall Mathias and Chessa Stefano and Coleman Sonya and Di Rocco Maurizio and Dragone Mauro and Gallicchio Claudio and Gennaro Claudio and Guzman Roberto and Lopez Raul and Lozano Hector and Maguire Liam and McGinnity T Martin and Micheli Alessio and O'Hare Greg MP and Pecora Federico and Ray AK and Renteria Arantxa and Saffiotti Alessandro and Swords David and Vairo Claudio},<br \/>\r\nyear  = {2012},<br \/>\r\ndate = {2012-01-01},<br \/>\r\nbooktitle = {Poster in the 5th International Conference on Cognitive Systems (CogSys 2012)},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {presentation}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('29','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2010\">2010<\/h3><div class=\"tp_publication tp_publication_techreport\"><div class=\"tp_pub_number\">8.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Davide, Bacciu;  Alessio, Micheli;  Alessandro, Sperduti<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('54','tp_links')\" style=\"cursor:pointer;\">A Bottom-up Hidden Tree Markov Model<\/a> <span class=\"tp_pub_type techreport\">Technical Report<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_institution\">Universit\u00e0 di Pisa <\/span><span class=\"tp_pub_additional_number\">no. TR-10-08, <\/span><span class=\"tp_pub_additional_year\">2010<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_54\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('54','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_54\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('54','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_54\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@techreport{11568_254437,<br \/>\r\ntitle = {A Bottom-up Hidden Tree Markov Model},<br \/>\r\nauthor = {Bacciu Davide and Micheli Alessio and Sperduti Alessandro},<br \/>\r\nurl = {http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-10-08.pdf.gz},<br \/>\r\nyear  = {2010},<br \/>\r\ndate = {2010-04-01},<br \/>\r\nurldate = {2010-04-01},<br \/>\r\nvolume = {TR-10-08},<br \/>\r\nnumber = {TR-10-08},<br \/>\r\npages = {1--22},<br \/>\r\ninstitution = {Universit\u00e0 di Pisa},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {techreport}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('54','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_54\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-10-08.pdf.gz\" title=\"http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-10-08.pdf.gz\" target=\"_blank\">http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-10-08.pdf.gz<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('54','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"A Bottom-up Hidden Tree Markov Model\" src=\"http:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2016\/03\/cherubino.png\" width=\"80\" alt=\"A Bottom-up Hidden Tree Markov Model\" \/><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2009\">2009<\/h3><div class=\"tp_publication tp_publication_techreport\"><div class=\"tp_pub_number\">9.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Davide, Bacciu;  Grazia, Buscemi Maria;  Lusine, Mkrtchyan<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('99','tp_links')\" style=\"cursor:pointer;\">Adaptive Service Selection - A Fuzzy-valued Matchmaking Approach<\/a> <span class=\"tp_pub_type techreport\">Technical Report<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_institution\">Dipartimento di Informatica, Universita' di Pisa <\/span><span class=\"tp_pub_additional_techtype\">Technical Report, <\/span><span class=\"tp_pub_additional_number\">no. TR-09-21, <\/span><span class=\"tp_pub_additional_year\">2009<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_99\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('99','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_99\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('99','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_99\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@techreport{matchmakingTR09,<br \/>\r\ntitle = {Adaptive Service Selection - A Fuzzy-valued Matchmaking Approach},<br \/>\r\nauthor = {Bacciu Davide and Buscemi Maria Grazia and Mkrtchyan Lusine},<br \/>\r\nurl = {http:\/\/eprints.adm.unipi.it\/id\/eprint\/2241},<br \/>\r\nyear  = {2009},<br \/>\r\ndate = {2009-10-01},<br \/>\r\nurldate = {2009-10-01},<br \/>\r\nnumber = {TR-09-21},<br \/>\r\ninstitution = {Dipartimento di Informatica, Universita' di Pisa},<br \/>\r\ntype = {Technical Report},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {techreport}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('99','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_99\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/eprints.adm.unipi.it\/id\/eprint\/2241\" title=\"http:\/\/eprints.adm.unipi.it\/id\/eprint\/2241\" target=\"_blank\">http:\/\/eprints.adm.unipi.it\/id\/eprint\/2241<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('99','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Adaptive Service Selection - A Fuzzy-valued Matchmaking Approach\" src=\"http:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2016\/03\/cherubino.png\" width=\"80\" alt=\"Adaptive Service Selection - A Fuzzy-valued Matchmaking Approach\" \/><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2008\">2008<\/h3><div class=\"tp_publication tp_publication_phdthesis\"><div class=\"tp_pub_number\">10.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Davide, Bacciu<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('73','tp_links')\" style=\"cursor:pointer;\">A Perceptual Learning Model to Discover the Hierarchical Latent Structure of Image Collections<\/a> <span class=\"tp_pub_type phdthesis\">PhD Thesis<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_year\">2008<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_abstract_link\"><a id=\"tp_abstract_sh_73\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('73','tp_abstract')\" title=\"Show abstract\" style=\"cursor:pointer;\">Abstract<\/a><\/span> | <span class=\"tp_resource_link\"><a id=\"tp_links_sh_73\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('73','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_73\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('73','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_73\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@phdthesis{11568_466874,<br \/>\r\ntitle = {A Perceptual Learning Model to Discover the Hierarchical Latent Structure of Image Collections},<br \/>\r\nauthor = { Bacciu Davide},<br \/>\r\nurl = {http:\/\/e-theses.imtlucca.it\/id\/eprint\/7},<br \/>\r\ndoi = {10.6092\/imtlucca\/e-theses\/7},<br \/>\r\nyear  = {2008},<br \/>\r\ndate = {2008-01-01},<br \/>\r\nurldate = {2008-01-01},<br \/>\r\npublisher = {IMT Lucca},<br \/>\r\nabstract = {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\u2019s 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\u2019s 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.},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {phdthesis}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('73','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_abstract\" id=\"tp_abstract_73\" style=\"display:none;\"><div class=\"tp_abstract_entry\">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\u2019s 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\u2019s 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.<\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('73','tp_abstract')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_73\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/e-theses.imtlucca.it\/id\/eprint\/7\" title=\"http:\/\/e-theses.imtlucca.it\/id\/eprint\/7\" target=\"_blank\">http:\/\/e-theses.imtlucca.it\/id\/eprint\/7<\/a><\/li><li><i class=\"ai ai-doi\"><\/i><a class=\"tp_pub_list\" href=\"https:\/\/dx.doi.org\/10.6092\/imtlucca\/e-theses\/7\" title=\"Follow DOI:10.6092\/imtlucca\/e-theses\/7\" target=\"_blank\">doi:10.6092\/imtlucca\/e-theses\/7<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('73','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"A Perceptual Learning Model to Discover the Hierarchical Latent Structure of Image Collections\" src=\"https:\/\/www.imtlucca.it\/sites\/default\/themes\/agid\/img\/Logo_eng.png\" width=\"80\" alt=\"A Perceptual Learning Model to Discover the Hierarchical Latent Structure of Image Collections\" \/><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2007\">2007<\/h3><div class=\"tp_publication tp_publication_techreport\"><div class=\"tp_pub_number\">11.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Davide, Bacciu;  Alessio, Micheli;  Antonina, Starita<\/p><p class=\"tp_pub_title\"><a class=\"tp_title_link\" onclick=\"teachpress_pub_showhide('53','tp_links')\" style=\"cursor:pointer;\">Feature-wise Competitive Repetition Suppression Learning for Gene Data Clustering and Feature Ranking<\/a> <span class=\"tp_pub_type techreport\">Technical Report<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_institution\">Universit\u00e0 di Pisa <\/span><span class=\"tp_pub_additional_year\">2007<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_resource_link\"><a id=\"tp_links_sh_53\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('53','tp_links')\" title=\"Show links and resources\" style=\"cursor:pointer;\">Links<\/a><\/span> | <span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_53\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('53','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_53\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@techreport{11568_255939,<br \/>\r\ntitle = {Feature-wise Competitive Repetition Suppression Learning for Gene Data Clustering and Feature Ranking},<br \/>\r\nauthor = {Bacciu Davide and Micheli Alessio and Starita Antonina},<br \/>\r\nurl = {http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-07-04.pdf.gz},<br \/>\r\nyear  = {2007},<br \/>\r\ndate = {2007-01-01},<br \/>\r\nurldate = {2007-01-01},<br \/>\r\nvolume = {TR-07-04},<br \/>\r\npages = {1--14},<br \/>\r\ninstitution = {Universit\u00e0 di Pisa},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {techreport}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('53','tp_bibtex')\">Close<\/a><\/p><\/div><div class=\"tp_links\" id=\"tp_links_53\" style=\"display:none;\"><div class=\"tp_links_entry\"><ul class=\"tp_pub_list\"><li><i class=\"fas fa-globe\"><\/i><a class=\"tp_pub_list\" href=\"http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-07-04.pdf.gz\" title=\"http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-07-04.pdf.gz\" target=\"_blank\">http:\/\/compass2.di.unipi.it\/TR\/Files\/TR-07-04.pdf.gz<\/a><\/li><\/ul><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('53','tp_links')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Feature-wise Competitive Repetition Suppression Learning for Gene Data Clustering and Feature Ranking\" src=\"http:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2016\/03\/cherubino.png\" width=\"80\" alt=\"Feature-wise Competitive Repetition Suppression Learning for Gene Data Clustering and Feature Ranking\" \/><\/div><\/div><h3 class=\"tp_h3\" id=\"tp_h3_2003\">2003<\/h3><div class=\"tp_publication tp_publication_mastersthesis\"><div class=\"tp_pub_number\">12.<\/div><div class=\"tp_pub_info\"><p class=\"tp_pub_author\"> Davide, Bacciu<\/p><p class=\"tp_pub_title\">Neural Architectures for Learning the Internal Model of an Anthropomorphic Robot Arm <span class=\"tp_pub_type mastersthesis\">Masters Thesis<\/span> <\/p><p class=\"tp_pub_additional\"><span class=\"tp_pub_additional_school\">M.Sc. Thesis in Computer Science, Universita' di Pisa, <\/span><span class=\"tp_pub_additional_year\">2003<\/span><span class=\"tp_pub_additional_note\">, (In Italian)<\/span>.<\/p><p class=\"tp_pub_menu\"><span class=\"tp_bibtex_link\"><a id=\"tp_bibtex_sh_100\" class=\"tp_show\" onclick=\"teachpress_pub_showhide('100','tp_bibtex')\" title=\"Show BibTeX entry\" style=\"cursor:pointer;\">BibTeX<\/a><\/span><\/p><div class=\"tp_bibtex\" id=\"tp_bibtex_100\" style=\"display:none;\"><div class=\"tp_bibtex_entry\"><pre>@mastersthesis{mscThesis03,<br \/>\r\ntitle = {Neural Architectures for Learning the Internal Model of an Anthropomorphic Robot Arm},<br \/>\r\nauthor = {Bacciu Davide},<br \/>\r\nyear  = {2003},<br \/>\r\ndate = {2003-12-16},<br \/>\r\nurldate = {2003-12-16},<br \/>\r\nschool = {M.Sc. Thesis in Computer Science, Universita' di Pisa},<br \/>\r\nnote = {In Italian},<br \/>\r\nkeywords = {},<br \/>\r\npubstate = {published},<br \/>\r\ntppubtype = {mastersthesis}<br \/>\r\n}<br \/>\r\n<\/pre><\/div><p class=\"tp_close_menu\"><a class=\"tp_close\" onclick=\"teachpress_pub_showhide('100','tp_bibtex')\">Close<\/a><\/p><\/div><\/div><div class=\"tp_pub_image_right\"><img decoding=\"async\" name=\"Neural Architectures for Learning the Internal Model of an Anthropomorphic Robot Arm\" src=\"http:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2016\/03\/cherubino.png\" width=\"80\" alt=\"Neural Architectures for Learning the Internal Model of an Anthropomorphic Robot Arm\" \/><\/div><\/div><\/div><\/div><\/code><\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":19,"featured_media":0,"parent":13,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-1388","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/pages\/1388","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/users\/19"}],"replies":[{"embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/comments?post=1388"}],"version-history":[{"count":5,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/pages\/1388\/revisions"}],"predecessor-version":[{"id":1525,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/pages\/1388\/revisions\/1525"}],"up":[{"embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/pages\/13"}],"wp:attachment":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/media?parent=1388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}