Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862075
Xavier Gonzalez-Olvera, Luis-Felipe Rodríguez
Computational models of emotions (CMEs) are software systems designed to synthesize the mechanisms of the human emotion process. They are included in cognitive agent architectures to endow Autonomous Agents (AAs) with abilities for the evaluation of emotional stimuli, the simulation and expression of emotional feelings, and the development of emotionally driven responses. Although the literature reports several developments of CMEs, there is still a wide range of challenges that remain unaddressed regarding their development process. A key challenge is the development of scalable CMEs whose architecture is capable of implementing novel findings about human emotions. In this paper, we discuss the challenge of scalable CMEs and present a case study that demonstrates how the step by step application of a methodology that takes advantage of psychological and biological findings leads to the design of scalable CMEs. The results of this paper aim at promoting the development of AAs capable of meeting the complex requirements of current applications.
{"title":"Towards scalable computational models of emotions for autonomous agents","authors":"Xavier Gonzalez-Olvera, Luis-Felipe Rodríguez","doi":"10.1109/ICCI-CC.2016.7862075","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862075","url":null,"abstract":"Computational models of emotions (CMEs) are software systems designed to synthesize the mechanisms of the human emotion process. They are included in cognitive agent architectures to endow Autonomous Agents (AAs) with abilities for the evaluation of emotional stimuli, the simulation and expression of emotional feelings, and the development of emotionally driven responses. Although the literature reports several developments of CMEs, there is still a wide range of challenges that remain unaddressed regarding their development process. A key challenge is the development of scalable CMEs whose architecture is capable of implementing novel findings about human emotions. In this paper, we discuss the challenge of scalable CMEs and present a case study that demonstrates how the step by step application of a methodology that takes advantage of psychological and biological findings leads to the design of scalable CMEs. The results of this paper aim at promoting the development of AAs capable of meeting the complex requirements of current applications.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130712375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862090
Kazutaka Nishiwaki, K. Kanamori, H. Ohwada
Numerous databases of DNA-microarrays are now widely available on the internet. Recently, there has been increasing interest in the analysis of microarray data using machine-learning techniques due to the amount of data, which is too massive for researchers to analyze using conventional techniques. In this study, we propose a method of finding a disease-related gene from microarray data using random forest, a machine-learning technique. More specifically, we focused on Alzheimer's disease and used microarray data related to Alzheimer's disease in the experiments. In the result, we found some genes that are believed to be related to Alzheimer's disease. Some genes discovered in the result have been investigated for their relevance to Alzheimer's disease, and this proves that our proposed methodology was successful in finding disease-related genes using microarray data. In addition, the proposed methodology is useful in providing new knowledge for biologists, medical scientists, and cognitive computing researchers since there is no previous work on genes that focused on finding a disease-related gene for Alzheimer's disease.
{"title":"Finding a disease-related gene from microarray data using random forest","authors":"Kazutaka Nishiwaki, K. Kanamori, H. Ohwada","doi":"10.1109/ICCI-CC.2016.7862090","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862090","url":null,"abstract":"Numerous databases of DNA-microarrays are now widely available on the internet. Recently, there has been increasing interest in the analysis of microarray data using machine-learning techniques due to the amount of data, which is too massive for researchers to analyze using conventional techniques. In this study, we propose a method of finding a disease-related gene from microarray data using random forest, a machine-learning technique. More specifically, we focused on Alzheimer's disease and used microarray data related to Alzheimer's disease in the experiments. In the result, we found some genes that are believed to be related to Alzheimer's disease. Some genes discovered in the result have been investigated for their relevance to Alzheimer's disease, and this proves that our proposed methodology was successful in finding disease-related genes using microarray data. In addition, the proposed methodology is useful in providing new knowledge for biologists, medical scientists, and cognitive computing researchers since there is no previous work on genes that focused on finding a disease-related gene for Alzheimer's disease.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125551029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862051
Hongbo Wang, Kezheng Wang, Y. Xue, Xuyan Tu
In real-time high dimensions optimization problem, how to quickly find the optimal solution and give timely response or decisive adjustment is very important. Inspired by the mutual parasitic behaviors, this paper suggests a new PSO variant, Cooperative Compounded Particle Swarm Optimization (COMPSO) that improves the convergence speed and reduces the possibility of particles into the local optimum. By using of real encoding mechanism, COMPSO is applied to the vehicle routing problem. Compared with other PSO algorithms, experimental results show the superiority of COMPSO algorithm in terms of the solution quality and computational efficiency. It proves a helpful guiding significance.
{"title":"Cooperative Compounded Particle Swarm Optimization and application","authors":"Hongbo Wang, Kezheng Wang, Y. Xue, Xuyan Tu","doi":"10.1109/ICCI-CC.2016.7862051","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862051","url":null,"abstract":"In real-time high dimensions optimization problem, how to quickly find the optimal solution and give timely response or decisive adjustment is very important. Inspired by the mutual parasitic behaviors, this paper suggests a new PSO variant, Cooperative Compounded Particle Swarm Optimization (COMPSO) that improves the convergence speed and reduces the possibility of particles into the local optimum. By using of real encoding mechanism, COMPSO is applied to the vehicle routing problem. Compared with other PSO algorithms, experimental results show the superiority of COMPSO algorithm in terms of the solution quality and computational efficiency. It proves a helpful guiding significance.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127655336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.4018/IJSSCI.2016100103
Rui Xu, Z. Li, P. Cui, Shengying Zhu, Ai Gao
Temporal reasoning is one of the cognitive capabilities humans involve in communicating with others and everything appears related because of temporal reference. Therefore, in this paper a geometric dynamic temporal reasoning algorithm is proposed to solve the temporal reasoning problem, especially in autonomous planning and scheduling. This method is based on the representation of actions in a two dimensional coordination system. The main advantage of this method over others is that it uses tags to mark new constraints added into the constraint network, which leads the algorithm to deal with pending constraints rather than all constraints. This characteristic makes the algorithm suitable for temporal reasoning, where variables and constraints are always added dynamically. This algorithm can be used not only in intelligent planning, but also computational intelligence, real-time systems, and etc. The results show the efficiency of our algorithm from four cases simulating the planning and scheduling process.
{"title":"A geometric dynamic temporal reasoning method with tags","authors":"Rui Xu, Z. Li, P. Cui, Shengying Zhu, Ai Gao","doi":"10.4018/IJSSCI.2016100103","DOIUrl":"https://doi.org/10.4018/IJSSCI.2016100103","url":null,"abstract":"Temporal reasoning is one of the cognitive capabilities humans involve in communicating with others and everything appears related because of temporal reference. Therefore, in this paper a geometric dynamic temporal reasoning algorithm is proposed to solve the temporal reasoning problem, especially in autonomous planning and scheduling. This method is based on the representation of actions in a two dimensional coordination system. The main advantage of this method over others is that it uses tags to mark new constraints added into the constraint network, which leads the algorithm to deal with pending constraints rather than all constraints. This characteristic makes the algorithm suitable for temporal reasoning, where variables and constraints are always added dynamically. This algorithm can be used not only in intelligent planning, but also computational intelligence, real-time systems, and etc. The results show the efficiency of our algorithm from four cases simulating the planning and scheduling process.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125249482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862073
L. Barghout
With the recent stunning success of machine learning, artificially intelligent machine vision research falls (roughly) into two camps: the big data camp and cognitive informatics camp. Big data uses statistical methods to discover latent structures that emerge from the co-occurrences of relevant features when sampling over enormous quantities of data. The cognitive informatics methods design computer vision systems to mimic human cognition. Though some visual latent features that emerge from deep learning networks, mimic mammalian visual detectors, as of yet the information processing mechanisms (analogous to human psychophysical mechanisms) remain hidden within the complexity of the deep nets. Furthermore, the sampling requirements of big data systems require limiting samples to pre-processed sets, such as SHIFT (shift invariant feature transform (Lowe 1999)). Techniques, such as the ones introduced in this paper, provide fast cognitively relevant methods for selecting samples and reducing the number of candidate features. The approach described in this paper live squarely in the camp of designing computer vision A.I. to mimics human cognitive processes. I introduce a novel definition of edges, based on human hierarchical scene perception. Hierarchical scene perception views vision within the 5 dimensions of horizontal & vertical position, depth, time and scene abstraction level (spatial-taxon). Fuzzy inference selects candidate edge elements using the Gestalt psychology principal of good curvilinear continuation, proximity and edges attachment. Spatial-taxon inference infers an edge outline for each level of abstraction within the scene architecture. The system was tested on 60 natural images and the results provide edges more aligned with human intuition of what edges should look like. ROC plots indicate solid performance, with the majority of human subjects rating the edge detection as high quality. The inferred edges are consistent with the finding of neurons responsive to proto-object boundaries in the visual cortex.
{"title":"Using the 5th dimensions of human visual perception to inspire automated edge and texture segmentation: A fuzzy spatial-taxon approach","authors":"L. Barghout","doi":"10.1109/ICCI-CC.2016.7862073","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862073","url":null,"abstract":"With the recent stunning success of machine learning, artificially intelligent machine vision research falls (roughly) into two camps: the big data camp and cognitive informatics camp. Big data uses statistical methods to discover latent structures that emerge from the co-occurrences of relevant features when sampling over enormous quantities of data. The cognitive informatics methods design computer vision systems to mimic human cognition. Though some visual latent features that emerge from deep learning networks, mimic mammalian visual detectors, as of yet the information processing mechanisms (analogous to human psychophysical mechanisms) remain hidden within the complexity of the deep nets. Furthermore, the sampling requirements of big data systems require limiting samples to pre-processed sets, such as SHIFT (shift invariant feature transform (Lowe 1999)). Techniques, such as the ones introduced in this paper, provide fast cognitively relevant methods for selecting samples and reducing the number of candidate features. The approach described in this paper live squarely in the camp of designing computer vision A.I. to mimics human cognitive processes. I introduce a novel definition of edges, based on human hierarchical scene perception. Hierarchical scene perception views vision within the 5 dimensions of horizontal & vertical position, depth, time and scene abstraction level (spatial-taxon). Fuzzy inference selects candidate edge elements using the Gestalt psychology principal of good curvilinear continuation, proximity and edges attachment. Spatial-taxon inference infers an edge outline for each level of abstraction within the scene architecture. The system was tested on 60 natural images and the results provide edges more aligned with human intuition of what edges should look like. ROC plots indicate solid performance, with the majority of human subjects rating the edge detection as high quality. The inferred edges are consistent with the finding of neurons responsive to proto-object boundaries in the visual cortex.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117277249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862081
Mohammed Falih Hassan, I. Abdel-Qader
In order to improve classification accuracy, multiple classifier systems have provided better pattern classification over single classifier systems in different applications. The theoretical frameworks proposed in [5], [7] present important tools for estimating and minimizing the added error of linearly combined classifier systems. In this work, we present a theoretical model that estimates the added error using geometric mean rule which is a nonlinear combining rule. In the derivation, we assume classifiers' outputs are uncorrelated and have identical distributions for a given class case. We also show that by setting the number of classifiers to one (a single classifier system), the derived formula is modified and matches the results given in [5]. We validated our derivations with computer simulations and compared these with the analytical results. Due to the nonlinearity of the geometric mean, theoretical results show that the bias and variance errors are mixed together in their contribution to the added error. It was shown that the bias error dominated the contribution to the added error compared to the variance error. It is possible to minimize the variance error by increasing the ensemble size (number of classifiers) while the bias error is minimized under certain conditions. The proposed theoretical work can help in investigating the added error for other nonlinear arithmetic combining rules.
{"title":"Improving pattern classification by nonlinearly combined classifiers","authors":"Mohammed Falih Hassan, I. Abdel-Qader","doi":"10.1109/ICCI-CC.2016.7862081","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862081","url":null,"abstract":"In order to improve classification accuracy, multiple classifier systems have provided better pattern classification over single classifier systems in different applications. The theoretical frameworks proposed in [5], [7] present important tools for estimating and minimizing the added error of linearly combined classifier systems. In this work, we present a theoretical model that estimates the added error using geometric mean rule which is a nonlinear combining rule. In the derivation, we assume classifiers' outputs are uncorrelated and have identical distributions for a given class case. We also show that by setting the number of classifiers to one (a single classifier system), the derived formula is modified and matches the results given in [5]. We validated our derivations with computer simulations and compared these with the analytical results. Due to the nonlinearity of the geometric mean, theoretical results show that the bias and variance errors are mixed together in their contribution to the added error. It was shown that the bias error dominated the contribution to the added error compared to the variance error. It is possible to minimize the variance error by increasing the ensemble size (number of classifiers) while the bias error is minimized under certain conditions. The proposed theoretical work can help in investigating the added error for other nonlinear arithmetic combining rules.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114927204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Prototype reduction is aimed at reducing prohibitive computational costs and the storage space for pattern recognition. The most frequently used methods include the condensating and editing approaches. Condensating method removes the patterns far from the decision boundary and do not contribute to better classification accuracy, while editing method removes noise patterns to improve the classification accuracy. In this paper, a new hybrid algorithm called prototype reduction algorithm based on natural neighbor and nearest enemy is presented. At first, an editing algorithm is proposed to filter noisy patterns and smooth the class boundaries by using the concept of natural neighbor. The main advantage of the editing algorithm is that it does not require any user-defined parameters. Then, using a new condensing method based on nearest enemy to reduce prototypes far from decision line. Through this algorithm, interior prototypes are discarded. Experiments show that the hybrid approach effectively reduces the number of prototypes while achieves higher classification performance along with competitive prototype algorithms.
{"title":"An efficient reduction algorithm based on natural neighbor and nearest enemy","authors":"Lijun Yang, Qingsheng Zhu, Jinlong Huang, Dongdong Cheng","doi":"10.1109/ICCI-CC.2016.7862037","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862037","url":null,"abstract":"Prototype reduction is aimed at reducing prohibitive computational costs and the storage space for pattern recognition. The most frequently used methods include the condensating and editing approaches. Condensating method removes the patterns far from the decision boundary and do not contribute to better classification accuracy, while editing method removes noise patterns to improve the classification accuracy. In this paper, a new hybrid algorithm called prototype reduction algorithm based on natural neighbor and nearest enemy is presented. At first, an editing algorithm is proposed to filter noisy patterns and smooth the class boundaries by using the concept of natural neighbor. The main advantage of the editing algorithm is that it does not require any user-defined parameters. Then, using a new condensing method based on nearest enemy to reduce prototypes far from decision line. Through this algorithm, interior prototypes are discarded. Experiments show that the hybrid approach effectively reduces the number of prototypes while achieves higher classification performance along with competitive prototype algorithms.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129474849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862042
Aurelie Gaudieux, Joel Kwan, V. Sébastien, R. Courdier
This paper presents the SIEGMAS system (Stakeholders Interactions in Environmental Governance by a Multi-Agent System) designed to simulate interactions between stakeholders in common pool resources in Indian Ocean Islands. This decision support system tool is based on a model allowing the study of the interactions between agents acting on a territory and influenced by economic aspects thanks to an agronomic interface. The work presented here focuses on interactive and dynamic tools we developed in order to provide our system with powerful functionalities for maps' configuration and results interpretation. The purpose of this project is twofold. On one hand, we want to offer a tool devoted to the economists community working on Common Pool Resources. On the other hand, we want to present a computer system solution dedicated to simulations' results interpretation for decision-makers in business and politics.
{"title":"Stakeholders strategies' in common pool resources. Experimentation of a help tool to the decision with Multi-Agent based simulation for Indian Ocean","authors":"Aurelie Gaudieux, Joel Kwan, V. Sébastien, R. Courdier","doi":"10.1109/ICCI-CC.2016.7862042","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862042","url":null,"abstract":"This paper presents the SIEGMAS system (Stakeholders Interactions in Environmental Governance by a Multi-Agent System) designed to simulate interactions between stakeholders in common pool resources in Indian Ocean Islands. This decision support system tool is based on a model allowing the study of the interactions between agents acting on a territory and influenced by economic aspects thanks to an agronomic interface. The work presented here focuses on interactive and dynamic tools we developed in order to provide our system with powerful functionalities for maps' configuration and results interpretation. The purpose of this project is twofold. On one hand, we want to offer a tool devoted to the economists community working on Common Pool Resources. On the other hand, we want to present a computer system solution dedicated to simulations' results interpretation for decision-makers in business and politics.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115157609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862058
L. Huguet, N. Sabouret, D. Lourdeaux
In the context of medical team leaders training, we present a multiagent communication model that can introduce errors in a team of agents. This model is built from existing work from the literature in multiagents systems and information science, but also from a corpus of dialogues collected during actual field training for medical teams. Our model supports four types of communication errors (misunderstanding, misinterpretation, non-understanding and absence of answer) that appear at different stages of the communication process.
{"title":"“Errare Humanum Est”: Simulation of communication error among a virtual team in crisis situation","authors":"L. Huguet, N. Sabouret, D. Lourdeaux","doi":"10.1109/ICCI-CC.2016.7862058","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862058","url":null,"abstract":"In the context of medical team leaders training, we present a multiagent communication model that can introduce errors in a team of agents. This model is built from existing work from the literature in multiagents systems and information science, but also from a corpus of dialogues collected during actual field training for medical teams. Our model supports four types of communication errors (misunderstanding, misinterpretation, non-understanding and absence of answer) that appear at different stages of the communication process.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128602343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862024
R. Fiorini
In a previous paper we showed and discussed how computational information conservation theory (CICT) can help us to develop even competitive advanced quantum cognitive computational systems. To achieve reliable system intelligence outstanding results, current computational system modeling and simulation community has to face and to solve two orders of modeling limitations at least. As a solution, we propose an exponential, prespatial arithmetic scheme (“all-powerful scheme”) by CICT to overcome the Information Double-Bind (IDB) problem and to thrive on both deterministic noise (DN) and random noise (RN) to develop powerful cognitive computational frameworks for deep learning, towards deep thinking applications. An operative example is presented. This paper is a relevant contribution towards an effective and convenient “Science 2.0” universal computational framework to develop deeper learning and deep thinking system and application at your fingertips and beyond.
{"title":"Deep learning and deep thinking: New application framework by CICT","authors":"R. Fiorini","doi":"10.1109/ICCI-CC.2016.7862024","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862024","url":null,"abstract":"In a previous paper we showed and discussed how computational information conservation theory (CICT) can help us to develop even competitive advanced quantum cognitive computational systems. To achieve reliable system intelligence outstanding results, current computational system modeling and simulation community has to face and to solve two orders of modeling limitations at least. As a solution, we propose an exponential, prespatial arithmetic scheme (“all-powerful scheme”) by CICT to overcome the Information Double-Bind (IDB) problem and to thrive on both deterministic noise (DN) and random noise (RN) to develop powerful cognitive computational frameworks for deep learning, towards deep thinking applications. An operative example is presented. This paper is a relevant contribution towards an effective and convenient “Science 2.0” universal computational framework to develop deeper learning and deep thinking system and application at your fingertips and beyond.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130048187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：