Landslides pose a significant risk to human life. The Twisting Theory (TWT) and Crown Clustering ... more Landslides pose a significant risk to human life. The Twisting Theory (TWT) and Crown Clustering Algorithm (CCA) are innovative adaptive algorithms that can determine the shape of a landslide and predict its future evolution based on the movement of position sensors located in the affected area. In the first part of this study, the TWT and CCA will be thoroughly explained from a mathematical and theoretical perspective. In the second part, these algorithms will be applied to real-life cases, the Assisi landslide (1995–2008) and the Corvara landslide (2000–2008). A correlation of 0.9997 was attained between the model estimates and the expert’s posterior measurements at both examined sites. The results of these applications reveal that the TWT can accurately identify the overall shape of the landslides and predict their progression, while the CCA identifies complex cause-and-effect relationships among the sensors and represents them in a clear, weighted graph. To apply this model to a...
Artificial Adaptive Systems Using Auto Contractive Maps, 2018
We have looked at how to visualize the relationships among the elements of a dataset in Chap. 4. ... more We have looked at how to visualize the relationships among the elements of a dataset in Chap. 4. This chapter is devoted to the use of Auto-CM in the transformation of datasets for the purpose of extracting further relationships among data elements. The first transformation we call the FS-Transform, which looks beyond an all or nothing, binary relationship that is typical of most ANNs. The extraction of these perhaps more subtle relationships can be thought of as gradual relationships, zero denoting no relationship is present and one denoting a full/complete relationship that is absolutely present. It is thus, akin to a fuzzy set. The second transformation is one, which “morph” the delineation between records and variables within records that we call Hyper-Composition.
One of the most powerful aspects of our approach to neural networks is not only the development o... more One of the most powerful aspects of our approach to neural networks is not only the development of the Auto-CM neural network but the visualization of its results. In this chapter we look at two visualization approaches—the Minimal Spanning Tree (MST) and the Maximal Regular Graph (MRG). The resultant from Auto-CM is a matrix of weights. This weight matrix naturally fits into a graph theoretic framework since the weights connecting the nodes will be viewed as edges and the weights as the weights on these edges.
This article examines the implicit space grammar of the cultural vibrancy of the region of Hallan... more This article examines the implicit space grammar of the cultural vibrancy of the region of Halland in Southwest Sweden. By using a new computational approach, we implement for the first time a methodology that allows us, on the one side, to extrapolate the complex dynamic evolution of the region’s cultural geography and, on the other side, to diagnose the structural causes of its eventual decay. The results provide a basis for a more systematic approach to evidence-based policy design at the regional scale, and for a more participatory, bottom-up public decision-making in the cultural and other policy spheres.
We propose an alternative approach to "deep" learning that is based on computational ec... more We propose an alternative approach to "deep" learning that is based on computational ecologies of structurally diverse artificial neural networks, and on dynamic associative memory responses to stimuli. Rather than focusing on massive computation of many different examples of a single situation, we opt for model-based learning and adaptive flexibility. Cross-fertilization of learning processes across multiple domains is the fundamental feature of human intelligence that must inform "new" artificial intelligence.
In this paper, we present an innovative data processing architecture, the Activation & Compet... more In this paper, we present an innovative data processing architecture, the Activation & Competition System (ACS), and show how this methodology allows us to reconstruct in detail some aspects of the fine grained structure of global relationships in the world order perspective, on the basis of a minimal dataset only consisting of the values of five publicly available indicators for 2007 for the 118 countries for which they are jointly available. ACS seems in particular to qualify as a valuable tool for the analysis of inter-country patterns of conflict and alliances, which may prove of special interest in the current situation of global strategic uncertainty in international relations.
International Journal of Information Systems and Social Change, 2015
Data sets collected independently using the same variables can be compared using a new artificial... more Data sets collected independently using the same variables can be compared using a new artificial neural network called Artificial neural network What If Theory, AWIT. Given a data set that is deemed the standard reference for some object, i.e. a flower, industry, disease, or galaxy, other data sets can be compared against it to identify its proximity to the standard. Thus, data that might not lend itself well to traditional methods of analysis could identify new perspectives or views of the data and thus, potentially new perceptions of novel and innovative solutions. This method comes out of the field of artificial intelligence, particularly artificial neural networks, and utilizes both machine learning and pattern recognition to display an innovative analysis.
Parte della letteratura sui distretti industriali considera l’agglomerazione di imprese come un f... more Parte della letteratura sui distretti industriali considera l’agglomerazione di imprese come un fenomeno strettamente dipendente dalla specializzazione settoriale. Il presente studio ha indagato le agglomerazioni spaziali di attività economiche, partendo dal presupposto della loro intrinseca complessità socio-economica, che rende talvolta unici i percorsi dello sviluppo locale. Al fine di rilevare la multi-dimensionalità di suddetti fenomeni e quindi di cogliere somiglianze
Landslides pose a significant risk to human life. The Twisting Theory (TWT) and Crown Clustering ... more Landslides pose a significant risk to human life. The Twisting Theory (TWT) and Crown Clustering Algorithm (CCA) are innovative adaptive algorithms that can determine the shape of a landslide and predict its future evolution based on the movement of position sensors located in the affected area. In the first part of this study, the TWT and CCA will be thoroughly explained from a mathematical and theoretical perspective. In the second part, these algorithms will be applied to real-life cases, the Assisi landslide (1995–2008) and the Corvara landslide (2000–2008). A correlation of 0.9997 was attained between the model estimates and the expert’s posterior measurements at both examined sites. The results of these applications reveal that the TWT can accurately identify the overall shape of the landslides and predict their progression, while the CCA identifies complex cause-and-effect relationships among the sensors and represents them in a clear, weighted graph. To apply this model to a...
Artificial Adaptive Systems Using Auto Contractive Maps, 2018
We have looked at how to visualize the relationships among the elements of a dataset in Chap. 4. ... more We have looked at how to visualize the relationships among the elements of a dataset in Chap. 4. This chapter is devoted to the use of Auto-CM in the transformation of datasets for the purpose of extracting further relationships among data elements. The first transformation we call the FS-Transform, which looks beyond an all or nothing, binary relationship that is typical of most ANNs. The extraction of these perhaps more subtle relationships can be thought of as gradual relationships, zero denoting no relationship is present and one denoting a full/complete relationship that is absolutely present. It is thus, akin to a fuzzy set. The second transformation is one, which “morph” the delineation between records and variables within records that we call Hyper-Composition.
One of the most powerful aspects of our approach to neural networks is not only the development o... more One of the most powerful aspects of our approach to neural networks is not only the development of the Auto-CM neural network but the visualization of its results. In this chapter we look at two visualization approaches—the Minimal Spanning Tree (MST) and the Maximal Regular Graph (MRG). The resultant from Auto-CM is a matrix of weights. This weight matrix naturally fits into a graph theoretic framework since the weights connecting the nodes will be viewed as edges and the weights as the weights on these edges.
This article examines the implicit space grammar of the cultural vibrancy of the region of Hallan... more This article examines the implicit space grammar of the cultural vibrancy of the region of Halland in Southwest Sweden. By using a new computational approach, we implement for the first time a methodology that allows us, on the one side, to extrapolate the complex dynamic evolution of the region’s cultural geography and, on the other side, to diagnose the structural causes of its eventual decay. The results provide a basis for a more systematic approach to evidence-based policy design at the regional scale, and for a more participatory, bottom-up public decision-making in the cultural and other policy spheres.
We propose an alternative approach to "deep" learning that is based on computational ec... more We propose an alternative approach to "deep" learning that is based on computational ecologies of structurally diverse artificial neural networks, and on dynamic associative memory responses to stimuli. Rather than focusing on massive computation of many different examples of a single situation, we opt for model-based learning and adaptive flexibility. Cross-fertilization of learning processes across multiple domains is the fundamental feature of human intelligence that must inform "new" artificial intelligence.
In this paper, we present an innovative data processing architecture, the Activation & Compet... more In this paper, we present an innovative data processing architecture, the Activation & Competition System (ACS), and show how this methodology allows us to reconstruct in detail some aspects of the fine grained structure of global relationships in the world order perspective, on the basis of a minimal dataset only consisting of the values of five publicly available indicators for 2007 for the 118 countries for which they are jointly available. ACS seems in particular to qualify as a valuable tool for the analysis of inter-country patterns of conflict and alliances, which may prove of special interest in the current situation of global strategic uncertainty in international relations.
International Journal of Information Systems and Social Change, 2015
Data sets collected independently using the same variables can be compared using a new artificial... more Data sets collected independently using the same variables can be compared using a new artificial neural network called Artificial neural network What If Theory, AWIT. Given a data set that is deemed the standard reference for some object, i.e. a flower, industry, disease, or galaxy, other data sets can be compared against it to identify its proximity to the standard. Thus, data that might not lend itself well to traditional methods of analysis could identify new perspectives or views of the data and thus, potentially new perceptions of novel and innovative solutions. This method comes out of the field of artificial intelligence, particularly artificial neural networks, and utilizes both machine learning and pattern recognition to display an innovative analysis.
Parte della letteratura sui distretti industriali considera l’agglomerazione di imprese come un f... more Parte della letteratura sui distretti industriali considera l’agglomerazione di imprese come un fenomeno strettamente dipendente dalla specializzazione settoriale. Il presente studio ha indagato le agglomerazioni spaziali di attività economiche, partendo dal presupposto della loro intrinseca complessità socio-economica, che rende talvolta unici i percorsi dello sviluppo locale. Al fine di rilevare la multi-dimensionalità di suddetti fenomeni e quindi di cogliere somiglianze
In this chapter presents a new paradigm of Artificial Neural Networks (ANNs): the Auto-Contractiv... more In this chapter presents a new paradigm of Artificial Neural Networks (ANNs): the Auto-Contractive Maps (Auto-CM). The Auto-CM differ from the traditional ANNs under many viewpoints: the Auto-CM start their learning task without a random initialization of their weights, they meet their convergence criterion when all their output nodes become null, their weights matrix develops a data driven warping of the original Euclidean space, they show suitable topological properties, etc. Further two new algorithms, theoretically linked to Auto-CM are presented: the first one is useful to evaluate the complexity and the topo-logical information of any kind of connected graph: the H Function is the index to measure the global hub-ness of the graph generated by the Auto-CM weights matrix. The second one is named Maximally Regular Graph (MRG) and it is an development of the traditionally Minimum Spanning Tree (MST). The Auto-Contractive Map (Auto-CM) presents a three layers architecture: an Input layer, where the signal is captured from the environment, an Hidden layer, where the signal is modulated inside the Auto-CM, and an Output layer by which the Auto-CM influences the environment according to the stimuli previously received (Figure 1). Each layer is composed by N units. Then the whole Auto-CM is composed by 3N units. The connections between the Input layer and the Hidden layer are Mono-dedicated, whereas the ones between the Hidden layer and the Output layer are at maximum gradient. Therefore, in relation to the units the number of the connections Nc, is given by: Nc = N (N + 1). Fig. 1. The figure gives an example of an Auto-CM with N = 4.
It has been shown that a new procedure (Implicit Function as Squashing Time, IFAST) based on Arti... more It has been shown that a new procedure (Implicit Function as Squashing Time, IFAST) based on Artificial Neural Networks (ANNs) is able to compress eyes-closed resting electroencephalographic (EEG) data into spatial invariants of the instant voltage distributions for an automatic classification of mild cognitive impairment (MCI) and Alzheimer's disease (AD) subjects with classification accuracy of individual subjects higher than 92%. In this chapter the method has been applied to distinguish individual normal elderly (Nold) vs. Mild Cognitive Impairment (MCI) subjects, an important issue for the screening of large populations at high risk of AD. Eyes-closed resting EEG data (10-20 electrode montage) were recorded in 171 Nold and in 115 amnesic MCI subjects. The data inputs for the classification by IFAST were the weights of the connections within a non linear auto-associative ANN trained to generate the instant voltage distributions of 60-s ar-tifact free EEG data. The most relevant features were selected and coincidently the dataset was split into two halves for the final binary classification (training and testing) performed by a supervised ANN. The classification of the individual Nold and MCI subjects reached 95.87% of sensitivity and 91.06% of specificity (93.46% of accuracy). These results indicate that IFAST can reliably distinguish eyes-closed resting EEG in individual Nold and MCI subjects, and may be used for large-scale periodic screening of large populations at risk of AD and personalized care.
In this chapter we present a new unsupervised artificial adaptive system, able to extract feature... more In this chapter we present a new unsupervised artificial adaptive system, able to extract features of interest in digital imaging, to reduce image noise maintaining the spatial resolution of high contrast structures and the expression of hidden morphological features. The new system, named J-Net, belongs to the family of ACM systems developed by Semeion Research Center. J-Net is able to isolate in an almost geological way different brightness layers in the same image. These layers seem to be invisible to the human eye and for the other mathematical imaging system. This ability of the J-Net can have important medical applications.
On tasks such as the recognition of handwritten digits, traditional methods from machine learning... more On tasks such as the recognition of handwritten digits, traditional methods from machine learning and computer vision have always failed to beat human performance. Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal. Our architecture could be summarized in two basic steps. First, we generate a diverse set of classification hypothesis using both Convo-lutional Neural Networks, currently the state-of-the-art technique for this task, among with other traditional and innovative machine learning techniques. Then, we optimally combine them through Meta-Nets, a family of recently developed and performing ensemble methods. In the resulting parliament of classifiers all hypothesis, despite of their accuracy or methodology, are considered. On the very competitive MNIST handwriting benchmark, our method is the first to beat human performance with 0.17% error rate, surprisingly showing diversity to be the key for success in decision making.
On tasks such as the recognition of handwritten digits, traditional methods from machine learning... more On tasks such as the recognition of handwritten digits, traditional methods from machine learning and computer vision have always failed to beat human performance. Inspired by the importance of diversity in biological system, we built an heterogeneous system that could achieve this goal. Our architecture could be summarized in two basic steps. First, we generate a diverse set of classification hypothesis using both Convo-lutional Neural Networks, currently the state-of-the-art technique for this task, among with other traditional and innovative machine learning techniques. Then, we optimally combine them through Meta-Nets, a family of recently developed and performing ensemble methods. In the resulting parliament of classifiers all hypothesis, despite of their accuracy or methodology, are considered. On the very competitive MNIST handwriting benchmark, our method is the first to beat human performance with 0.17% error rate, surprisingly showing diversity to be the key for success in decision making.
Uploads