Search

Your search keyword '"CIALFI Daniela"' showing total 198 results
Start Over Author "CIALFI Daniela"

Refine your results

more »

more »

more »

more »
198 results on '"CIALFI Daniela"'

1. KNOWLEDGE COMPLEXITY REACTION-DIFFUSION EQUATIONS WITH APPLICATION TO EASTERN EUROPE

Author

CIALFI Daniela and COLANTONIO Emiliano

Subjects
Knowledge diffusion, complexity nonlinear systems, Eastern Europe, reaction-diffusion equations, Knowledge Complexity Index, Business, HF5001-6182, Finance, HG1-9999
Abstract

Nowadays, there is an increasing focus on knowledge input and output measurement rather than assessing the characteristics of the knowledge itself. This phenomenon happens since knowledge becomes central into capitalistic production processes: the competitive advantage of countries is the principal engine for the production of high-value, non-ubiquitous and complex knowledge (see Dicken, 2007). In this paper, we present the reaction-diffusion equations and their application to a particular economic phenomenon: in which way knowledge complexity diffusion might affect or not affect the labour productivity across the Eastern European countries. More profoundly, the aim followed by the present research work is to provide Eastern European countries with a substitute approach: a strategy. This strategy has the objective of enabling these countries to avoid acting as knowledge predators towards other countries (i.e. those such as Sweden, Finland and Denmark, referred to as prey countries, which invest their resources in knowledge and therefore in technology). We simulate the knowledge competition and the spill-over productivity effects across the Eastern and some European countries using specific reaction-diffusion equations types: the Lotka-Volterra equations which are able to describe a complex dynamic system of the prey-predator phenomenon. Our approach is based on the two steps of analysis. In essence, the first step, we compute the Knowledge Complexity Index of patents, for quantifying the European knowledge complexity; describing the possible spatial patterns and transformation of the European knowledge. Furthermore, we use the canonical Lotka-Volterra models of patents from the European Patent Office and the labour productivity data from the Eurostat database from 2000 and 2017 for Eastern European countries and some European countries, such as Finland, Sweden, Austria and Germany. More specifically, we have identified the presence of lagged knowledge between the Eastern European countries and some Northern European, such as Finland, Sweden and Denmark. In conclusion, the implementation of specific knowledge diffusion policy strategies could be helpful for future applications. It may avoid intra-guild cannibalism phenomenon from being engaged in some Eastern European countries.

Published
2020

2. THE EUROPEAN TRANSLOCAL EMPOWERMENT: AN ECONOMETRIC APPROACH

Author

CIALFI Daniela and COLANTONIO Emiliano

Subjects
Translocal empowerment, social innovation, panel data method, cross-country analysis, Europe, Business, HF5001-6182, Finance, HG1-9999
Abstract

Nowadays, there are numerous initiatives in response to contemporary socio-economic challenges. One possible response could be the social innovation phenomenon defined, according to Avelino et al. (2017), as the changing of social relations and involving new way of doing things. In this context, the aim of the paper is to discuss the empowerment and the social innovations concept by developing the empowerment mechanisms under a social psychology point of view, at one side, and exploring, in an empirical way, how people are empowered through transactional linkages, the translocal network. In particular, it is necessary to identify which translocal empowerment dimension is present across the European countries via the selection and the analysis of the possible social innovation proxies. To do this, it is necessary to comprehend the social innovation determinants at the macro-economic level across the European countries. Using the Akgüҁ multivariate regression model (2019), the paper studies the role of one possible social innovation proxy: the social protection expenditure. Under a methodological point of view, this model is used since it allows the combination between the traditional macro-level variables and the innovative ones, such as cultural norms and fear of failure; and it permits the inclusion of the country-specific characteristics. It also takes into account the macro-economic circumstance, the international financial crisis of 2008 until 2017. This period of analysis permits to control if the international economic crisis in 2008 might have influenced in some way the translocal empowerment dimension and brings together a panel data of different indicators from different data sources, such as Eurostat and Global Entrepreneurship Monitor (GEM), which provides measures of the entrepreneurial behaviour within countries. As part of the robustness check, we have used social innovation measures that could include country fixed effects accounting the heterogeneities across European countries. What emerges from the present empirical study is that the translocal network could be considered as a crucial factor for the social innovation implementation, since social innovation actors might access the local resources, developing, at the same time, the ability to interface with the local institutions, present in the current socio-economic system.

Published
2019

3. THE EUROPEAN COMPLEX KNOWLEDGE

Author

CIALFI Daniela and COLANTONIO Emiliano

Subjects
network analysis, neural network, country performance, Europe, Business, HF5001-6182, Finance, HG1-9999
Abstract

Nowadays, it has been besetted with knowledge input and output measurement instead of analyze the quality of the knowledge produced. Since knowledge become central into capitalistic production processes, the competitive advantage of countries is the principal engine for the production of high-value, non-ubiquitous and complex knowledge (see Dicken, 2007). The aim of the present study is to measure the knowledge complexity of the European countries from 2004 to 2013, designing the knowledge evolution and distribution. One consequent intention is to examine in which way the spatial knowledge diffusion might be connected to complexity. To achieve these purposes, we identified the presence of the European country-tech knowledge network, used as starting point to compute the Knowledge Complexity Index, in which the technological classes are composed by the countries having an relative technological advantage in terms of patent spread. Subsequently, we used two distinct types of statistical analysis: the first, based on non-linear clustering with Self-Organizing Map (SOM hereafter) neural network, for evaluating the performance development of the European countries between 2004 and 2013, where, for example, Eat countries, located at the top of the map, show low values in almost all considered variables; and the second one, based on the Knowledge Complexity Index (KCI hereafter) of technological classes, for quantifying the European knowledge complexity; describing the possible spatial patterns and transformation of the European knowledge. What emerges from the present study is an inactive spatial state of art, in which only the Northern European countries produce the most conglomerate knowledge and technologies. In this structure, it is necessary to stress out that what affirmed previously could be considered the basis for the improvement and the achievement of the specific country’s innovation policy. However, under complex knowledge terms, the previous innovation policies might be assimilated with a useful tool for the increment of that technologies that present more complexity than the original ones.

Published
2019

4. A Primer on Gibsonian Information

Author

Alicea, Bradly, Cialfi, Daniela, Lim, Avery, and Parent, Jesse

Subjects
Quantitative Biology - Neurons and Cognition, Computer Science - Human-Computer Interaction
Abstract

Across the scientific literature, information measurement in the nervous system is posed as a problem of information processing internal to the brain by constructs such as neuronal populations, sensory surprise, or cognitive models. Application of information theory in the nervous system has focused on measuring phenomena such as capacity and integration. Yet the ecological perspective suggests that information is a product of active perception and interactions with the environment. Here, we propose Gibsonian Information (GI), relevant to both the study of cognitive agents and single cell systems that exhibit cognitive behaviors. We propose a formal model of GI that characterizes how agents extract environmental information in a dynamic fashion. GI demonstrates how sensory information guides information processing within individual nervous system representations of motion and continuous multisensory integration, as well as representations that guide collective behaviors. GI is useful for understanding first-order sensory inputs in terms of agent interactions with naturalistic contexts and simple internal representations and can be extended to cybernetic or symbolic representations. Statistical affordances, or clustered information that is spatiotemporally dependent perceptual input, facilitate extraction of GI from the environment. As a quantitative accounting of perceptual information, GI provides a means to measure a generalized indicator of nervous system input and can be characterized by three scenarios: disjoint distributions, contingent action, and coherent movement. By applying this framework to a variety of specific contexts, including a four-channel model of multisensory embodiment, we demonstrate how GI is essential to understanding the full scope of cognitive information processing., Comment: 48 pages, 10 figures, 2 tables

Published
2024

7. Are Birds Free from the Chains of the Skyway? Action Learning in a Cultural Context

Author

Edmonstone, John and Cialfi, Daniela

Abstract

The paper identifies what is meant by culture and examines approaches to mapping it, while suggesting alternatives. It notes the global spread of action learning, expressed through the prism of Western values, although practice is not necessarily reflective of the original ethos. It offers some rules of thumb on the use of action learning in different cultural settings and suggests a need for mutual adjustment and for research on action learning in a variety of cultural contexts.

Published
2023
Full Text
View/download PDF

11. The Self-Organizing Map: An Methodological Note

Author

Cialfi, Daniela, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Bucciarelli, Edgardo, editor, Chen, Shu-Heng, editor, and Corchado, Juan Manuel, editor

Published
2020
Full Text
View/download PDF

12. Mapping the Geography of Italian Knowledge

Author

Cialfi, Daniela, Colantonio, Emiliano, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Bucciarelli, Edgardo, editor, Chen, Shu-Heng, editor, and Corchado, Juan Manuel, editor

Published
2020
Full Text
View/download PDF

13. Do ICTs Matter for Italy?

Author

Cialfi, Daniela, Colantonio, Emiliano, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Bucciarelli, Edgardo, editor, Chen, Shu-Heng, editor, and Corchado, Juan Manuel, editor

Published
2019
Full Text
View/download PDF

20. Interpretable Models via Pairwise Permutations Algorithm

Author

Maasland, Troy, Pereira, João, Bastos, Diogo, de Goffau, Marcus, Nieuwdorp, Max, Zwinderman, Aeilko H., Levin, Evgeni, Kamp, Michael, Koprinska, Irena, Bibal, Adrien, Bouadi, Tassadit, Frénay, Benoît, Galárraga, Luis, Oramas, José, Adilova, Linara, Krishnamurthy, Yamuna, Kang, Bo, Largeron, Christine, Lijffijt, Jefrey, Viard, Tiphaine, Welke, Pascal, Ruocco, Massimiliano, Aune, Erlend, Gallicchio, Claudio, Schiele, Gregor, Pernkopf, Franz, Blott, Michaela, Fröning, Holger, Schindler, Günther, Guidotti, Riccardo, Monreale, Anna, Rinzivillo, Salvatore, Biecek, Przemyslaw, Ntoutsi, Eirini, Pechenizkiy, Mykola, Rosenhahn, Bodo, Buckley, Christopher, Cialfi, Daniela, Lanillos, Pablo, Ramstead, Maxwell, Verbelen, Tim, Ferreira, Pedro M., Andresini, Giuseppina, Malerba, Donato, Medeiros, Ibéria, Fournier-Viger, Philippe, Nawaz, M. Saqib, Ventura, Sebastian, Sun, Meng, Zhou, Min, Bitetta, Valerio, Bordino, Ilaria, Ferretti, Andrea, Gullo, Francesco, Ponti, Giovanni, Severini, Lorenzo, Ribeiro, Rita, Gama, João, Gavaldà, Ricard, Cooper, Lee, Ghazaleh, Naghmeh, Richiardi, Jonas, Roqueiro, Damian, Saldana Miranda, Diego, Sechidis, Konstantinos, Graça, Guilherme, Experimental Vascular Medicine, Vascular Medicine, ACS - Diabetes & metabolism, Amsterdam Gastroenterology Endocrinology Metabolism, Epidemiology and Data Science, APH - Methodology, Internal medicine, and AGEM - Endocrinology, metabolism and nutrition

Abstract

One of the most common pitfalls often found in high dimensional biological data sets are correlations between the features. This may lead to statistical and machine learning methodologies overvaluing or undervaluing these correlated predictors, while the truly relevant ones are ignored. In this paper, we will define a new method called pairwise permutation algorithm (PPA) with the aim of mitigating the correlation bias in feature importance values. Firstly, we provide a theoretical foundation, which builds upon previous work on permutation importance. PPA is then applied to a toy data set, where we demonstrate its ability to correct the correlation effect. We further test PPA on a microbiome shotgun dataset, to show that the PPA is already able to obtain biological relevant biomarkers.

Published
2021

22. Error Variance, Fairness, and the Curse on Minorities

Author

Beauxis-Aussalet, Emma, Kamp, Michael, Koprinska, Irena, Bibal, Adrien, Bouadi, Tassadit, Frénay, Benoît, Galárraga, Luis, Oramas, José, Adilova, Linara, Krishnamurthy, Yamuna, Kang, Bo, Largeron, Christine, Lijffijt, Jefrey, Viard, Tiphaine, Welke, Pascal, Ruocco, Massimiliano, Aune, Erlend, Gallicchio, Claudio, Schiele, Gregor, Pernkopf, Franz, Blott, Michaela, Fröning, Holger, Schindler, Günther, Guidotti, Riccardo, Monreale, Anna, Rinzivillo, Salvatore, Biecek, Przemyslaw, Ntoutsi, Eirini, Pechenizkiy, Mykola, Rosenhahn, Bodo, Buckley, Christopher, Cialfi, Daniela, Lanillos, Pablo, Ramstead, Maxwell, Verbelen, Tim, Ferreira, Pedro M., Andresini, Giuseppina, Malerba, Donato, Medeiros, Ibéria, Fournier-Viger, Philippe, Nawaz, M. Saqib, Ventura, Sebastian, Sun, Meng, Zhou, Min, Bitetta, Valerio, Bordino, Ilaria, Ferretti, Andrea, Gullo, Francesco, Ponti, Giovanni, Severini, Lorenzo, Ribeiro, Rita, Gama, João, Gavaldà, Ricard, Cooper, Lee, Ghazaleh, Naghmeh, Richiardi, Jonas, Roqueiro, Damian, Saldana Miranda, Diego, Sechidis, Konstantinos, Graça, Guilherme, Business Web and Media, Network Institute, Kamp, Michael, Koprinska, Irena, Bibal, Adrien, Bouadi, Tassadit, Frénay, Benoît, Galárraga, Luis, Oramas, José, Adilova, Linara, Krishnamurthy, Yamuna, Kang, Bo, Largeron, Christine, Lijffijt, Jefrey, Viard, Tiphaine, Welke, Pascal, Ruocco, Massimiliano, Aune, Erlend, Gallicchio, Claudio, Schiele, Gregor, Pernkopf, Franz, Blott, Michaela, Fröning, Holger, Schindler, Günther, Guidotti, Riccardo, Monreale, Anna, Rinzivillo, Salvatore, Biecek, Przemyslaw, Ntoutsi, Eirini, Pechenizkiy, Mykola, Rosenhahn, Bodo, Buckley, Christopher, Cialfi, Daniela, Lanillos, Pablo, Ramstead, Maxwell, Verbelen, Tim, Ferreira, Pedro M., Andresini, Giuseppina, Malerba, Donato, Medeiros, Ibéria, Fournier-Viger, Philippe, Nawaz, M. Saqib, Ventura, Sebastian, Sun, Meng, Zhou, Min, Bitetta, Valerio, Bordino, Ilaria, Ferretti, Andrea, Gullo, Francesco, Ponti, Giovanni, Severini, Lorenzo, Ribeiro, Rita, Gama, João, Gavaldà, Ricard, Cooper, Lee, Ghazaleh, Naghmeh, Richiardi, Jonas, Roqueiro, Damian, Saldana Miranda, Diego, Sechidis, Konstantinos, and Graça, Guilherme

Subjects
Fairness, Discrimination, Error variance, Transparency
Abstract

Machine learning systems can make more errors for certain populations and not others, and thus create discriminations. To assess such fairness issue, errors are typically compared across populations. We argue that we also need to account for the variability of errors in practice, as the errors measured in test data may not be exactly the same in real-life data (called target data). We first introduce statistical methods for estimating random error variance in machine learning problems. The methods estimate how often errors would exceed certain magnitudes, and how often the errors of a population would exceed that of another (e.g., by more than a certain range). The methods are based on well-established sampling theory, and the recently introduced Sample-to-Sample estimation. The latter shows that small target samples yield high error variance, even if the test sample is very large. We demonstrate that, in practice, minorities are bound to bear higher variance, thus amplified error and bias. This can occur even if the test and training sets are accurate, representative, and extremely large. We call this statistical phenomenon the curse on minorities, and we show examples of its impact with basic classification and regression problems. Finally, we outline potential approaches to protect minorities from such curse, and to develop variance-aware fairness assessments.

Published
2021

23. Review of CoViD-19, learning from the past: A wavelet and cross-correlation analysis of the epidemic dynamics looking to emergency calls and Twitter trends in Italian Lombardy region

Author

Cialfi, Daniela

Abstract

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/7640563. The author should better improve the following sections: Results: this section should be better formatted and made more clear if the Wavelet analysis and Cross-correlation and time delay analysis are incorporated within the main section (Result) or not. If yes, please incorporate these sub-sections accordingly; Results: the Figure mentioned within the section should be inserted upon their captions; The manuscript should be better formatted

Published
2021
Full Text
View/download PDF

27. Gibsonian Information: an agent-based paradigm for quantitative information

Author

Alicea, Bradly, Cialfi, Daniela, Lim, Anson, and Parent, Jesse

Abstract

We propose a theoretical framework of information based on Ecological Psychology called Gibsonian Information (GI). This framework is relevant to the study of cognitive agents and non-Neuronal systems (e.g. single cells) alike that exhibit cognitive behaviors. GI provides a framework to study how observers extract information out of direct perceptual information. GI differs from existing approaches such as optic flow, Shannon Information, or Bayesian surprise in two ways. The first involves an emphasis on the role of collective behavior and the dynamic evolution of systems. GI is particularly useful for understanding the information content of naturalistic contexts. Secondly, GI potentially allows us to distinguish the role of first-order sensory inputs in the context of higher-order representations. This allows us to extend GI to cybernetic and other types of symbolic systems representations. GI not only provides an alternate way to look at information in nervous systems, but also bolsters the role of information in the relationship between ecology and nervous systems.Our outline of the GI approach also considers the role of embodied observers during naturalistic perception, and how affordances influence the extraction of information from the environment. Along with attention, affordances are important in terms of funneling GI into the nervous system. When an affordance is encountered in the environment, it facilitates the extraction of GI from the environmental background. GI is meant to be a quantitative unit of spatial concentration in addition to being a generalized measure of nervous system input. To better understand GI as a measurable phenomenon, we characterize three model scenarios: disjoint distributions, contingent action, and coherent movement. All of these concepts provide a means to create a differential system between both motion (information) and random noise/stasis (non-information) and between the active sensory channel and information derived from mental representations. By applying this framework to a variety of specific contexts, including a four-channel model of multisensory embodiment, we demonstrate how GI is essential to understanding the full scope of cognitive information processing.

Published
2021
Full Text
View/download PDF

29. Embryo Networks as Generative Divergent Integration

Author

Alicea, Bradly and Cialfi, Daniela

Abstract

As the developmental phenotype grows and organizes, constituent cells engage in complex sets of interactions on their way to fully organized tissues. Networks can be extracted from the developmental phenotype based on the spatial proximity of cells, hypothetical signaling relationships, and physical connections. The generative nature of embryonic development (e.g. cell division and differentiation) results in networks that increasingly overlap but also diverge as developmental time elapses. This complexity emerges as a consequence of both functional differentiation and multiple scales of self-organization, from gene expression networks to anatomical networks. For newly dividing and differentiating cells in the embryo, network representations must incorporate new nodes and edges unique to the underlying generative process. In this submission, we will discuss integration of embryo networks and connectomes in development. These cellular-level networks provide us with networks of diverging and ultimately composite biological functions over time. While these networks describe and analyze a continuous structure, they also describe two dynamic processes: networks that grow and change shape over time, and network modules that exhibit divergent function over time. The two processes can be interpreted both in terms of attachment processes for newly-born (changes in structure) and newly-differentiated cells (changes in function). This model system might lead to new, biologically-specific principles for complex networks, particularly those that describe the paradox of divergent growth and connectivity processes under active functional integration.

Published
2021
Full Text
View/download PDF

31. This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition

Author

Nauta, Meike, Jutte, Annemarie, Provoost, Jesper, Seifert, Christin, Kamp, Michael, Koprinska, Irena, Bibal, Adrien, Bouadi, Tassadit, Frénay, Benoît, Galárraga, Luis, Oramas, José, Adilova, Linara, Krishnamurthy, Yamuna, Kang, Bo, Largeron, Christine, Lijffijt, Jefrey, Viard, Tiphaine, Welke, Pascal, Ruocco, Massimiliano, Aune, Erlend, Gallicchio, Claudio, Schiele, Gregor, Pernkopf, Franz, Blott, Michaela, Fröning, Holger, Schindler, Günther, Guidotti, Riccardo, Monreale, Anna, Rinzivillo, Salvatore, Biecek, Przemyslaw, Ntoutsi, Eirini, Pechenizkiy, Mykola, Rosenhahn, Bodo, Buckley, Christopher, Cialfi, Daniela, Lanillos, Pablo, Ramstead, Maxwell, Verbelen, Tim, Ferreira, Pedro M., Andresini, Giuseppina, Malerba, Donato, Medeiros, Ibéria, Fournier-Viger, Philippe, Nawaz, M. Saqib, Ventura, Sebastian, Sun, Meng, Zhou, Min, Bitetta, Valerio, Bordino, Ilaria, Ferretti, Andrea, Gullo, Francesco, Ponti, Giovanni, Severini, Lorenzo, Ribeiro, Rita, Gama, João, Gavaldà, Ricard, Cooper, Lee, Ghazaleh, Naghmeh, Richiardi, Jonas, Roqueiro, Damian, Saldana Miranda, Diego, Sechidis, Konstantinos, Graça, Guilherme, Datamanagement & Biometrics, and Digital Society Institute

Subjects
Informatik, Medizin, 22/1 OA procedure
Abstract

Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image “looks like” a prototype. However, perceptual similarity for humans can be different from the similarity learned by the classification model. Hence, only visualising prototypes can be insufficient for a user to understand what a prototype exactly represents, and why the model considers a prototype and an image to be similar. We address this ambiguity and argue that prototypes should be explained. We improve interpretability by automatically enhancing visual prototypes with quantitative information about visual characteristics deemed important by the classification model. Specifically, our method clarifies the meaning of a prototype by quantifying the influence of colour hue, shape, texture, contrast and saturation and can generate both global and local explanations. Because of the generality of our approach, it can improve the interpretability of any similarity-based method for prototypical image recognition. In our experiments, we apply our method to the existing Prototypical Part Network (ProtoPNet). Our analysis confirms that the global explanations are generalisable, and often correspond to the visually perceptible properties of a prototype. Our explanations are especially relevant for prototypes which might have been interpreted incorrectly otherwise. By explaining such ‘misleading’ prototypes, we improve the interpretability and simulatability of a prototype-based classification model. We also use our method to check whether visually similar prototypes have similar explanations, and are able to discover redundancy. Code is available at https://github.com/M-Nauta/Explaining_Prototypes.

Published
2021

34. Daniela Cialfi's contribution to the Discussion of 'the Discussion Meeting on Probabilistic and statistical aspects of machine learning'.

Author

Cialfi, Daniela

Subjects
MARKOV processes, GAUSSIAN distribution
Abstract

The article titled "From Denoising Diffusions to Denoising Markov Models" explores the use of denoising diffusion models in two ways: transforming data distribution into a Gaussian one and simulating approximate posterior simulation. The authors propose a framework that extends this approach to a wide range of spaces and introduces an original extension of score matching. The article suggests testing these models in real scenarios, such as theoretical neurobiology, to further explore their mathematical aspects. The author of the article is Daniela Cialfi. [Extracted from the article]

Published
2024
Full Text
View/download PDF

36. Learning One Abstract Bit at a Time Through Self-invented Experiments Encoded as Neural Networks

Author

Herrmann, Vincent, Kirsch, Louis, Schmidhuber, Jürgen, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

37. Probabilistic Majorization of Partially Observable Markov Decision Processes

Author

Lefebvre, Tom, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

38. Active Inference in Hebbian Learning Networks

Author

Safa, Ali, Verbelen, Tim, Keuninckx, Lars, Ocket, Ilja, Bourdoux, André, Catthoor, Francky, Gielen, Georges, Cauwenberghs, Gert, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

39. Efficient Motor Learning Through Action-Perception Cycles in Deep Kinematic Inference

Author

Priorelli, Matteo, Stoianov, Ivilin Peev, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

40. Integrating Cognitive Map Learning and Active Inference for Planning in Ambiguous Environments

Author

Van de Maele, Toon, Dhoedt, Bart, Verbelen, Tim, Pezzulo, Giovanni, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

41. On Embedded Normativity an Active Inference Account of Agency Beyond Flesh

Author

Guénin–Carlut, Avel, Albarracin, Mahault, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

42. Dynamical Perception-Action Loop Formation with Developmental Embodiment for Hierarchical Active Inference

Author

Esaki, Kanako, Matsumura, Tadayuki, Minusa, Shunsuke, Shao, Yang, Yoshimura, Chihiro, Mizuno, Hiroyuki, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

43. Relative Representations for Cognitive Graphs

Author

Kiefer, Alex B., Buckley, Christopher L., Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

44. Exploring Action-Centric Representations Through the Lens of Rate-Distortion Theory

Author

De Llanza Varona, Miguel, Buckley, Christopher, Millidge, Beren, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

45. An Analytical Model of Active Inference in the Iterated Prisoner’s Dilemma

Author

Demekas, Daphne, Heins, Conor, Klein, Brennan, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

46. Designing Explainable Artificial Intelligence with Active Inference: A Framework for Transparent Introspection and Decision-Making

Author

Albarracin, Mahault, Hipólito, Inês, Tremblay, Safae Essafi, Fox, Jason G., René, Gabriel, Friston, Karl, Ramstead, Maxwell J. D., Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

47. Towards Understanding Persons and Their Personalities with Cybernetic Big 5 Theory and the Free Energy Principle and Active Inference (FEP-AI) Framework

Author

Safron, Adam, Sheikhbahaee, Zahra, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

48. A Model of Agential Learning Using Active Inference

Author

Pitliya, Riddhi J., Murphy, Robin A., Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

49. Toward Design of Synthetic Active Inference Agents by Mere Mortals

Author

de Vries, Bert, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

50. Understanding Tool Discovery and Tool Innovation Using Active Inference

Author

Collis, Poppy, Kinghorn, Paul F., Buckley, Christopher L., Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, Verbelen, Tim, editor, and Wisse, Martijn, editor

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results