Papers by Magnus Johnsson
Biologically Inspired Cognitive Architectures, 2018
Bookmarks Related papers MentionsView impact
The 2021 Summit of the International Society for the Study of Information
Bookmarks Related papers MentionsView impact
International Conference on Neural Computation, Nov 30, 2016
Bookmarks Related papers MentionsView impact
We present a study of supervised neural network architectures capable of internal simulation of p... more We present a study of supervised neural network architectures capable of internal simulation of perceptions and actions. These architectures employ the novel Associative Self-Organizing Map (A-SOM) as a hidden layer (for the representation of perceptions), and a neural network adapted by the delta rule as an output layer (for the representation of actions). The A-SOM develops a representation of its in-put space, but in addition it also learns to associate its activity with an arbitrary number of additional (possibly delayed) inputs. We test architectures, with as well as without, recurrent connections. The simulation results are very encouraging. The architecture without recurrent connections correctly classified 100 % of the training samples and 80 % of the test samples. After ceasing to receive any input the best of the architectures with recurrent connections was able to continue to produce 100% correct output sequences for 28 epochs (280 iterations), and then to continue with 9...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Abstract. We present a system that can learn to represent actions as well as to internally simula... more Abstract. We present a system that can learn to represent actions as well as to internally simulate the likely continuation of their initial parts. The method we propose is based on the Associative Self Organizing Map (A-SOM), a variant of the Self Organizing Map. By emulating the way the human brain is thought to perform pattern recognition tasks, the A-SOM learns to associate its activity with different inputs over time, where inputs are observations of other’s actions. Once the A-SOM has learnt to recognize actions, it uses this learning to predict the continuation of an observed initial movement of an agent, in this way reading its intentions. We evaluate the system’s ability to simulate actions in an experiment with good results, and we provide a discussion about its generalization ability. The presented research is part of a bigger project aiming at en-dowing an agent with the ability to internally represent action patterns and to use these to recognize and simulate others beh...
Bookmarks Related papers MentionsView impact
Biologically Inspired Cognitive Architectures, 2017
Bookmarks Related papers MentionsView impact
Fertility rates have dramatically decreased in the last two decades, especially in men. It has be... more Fertility rates have dramatically decreased in the last two decades, especially in men. It has been described that environmental factors as well as life habits may affect semen quality. In this paper we use artificial intelligence techniques in order to predict semen characteristics from environmental factors, life habits and health status, as a possible Decision Support System that can help in the study of the male fertility potential. One hundred twenty three young healthy volunteers provide a semen sample that was analyzed according to the World Health Organization 2010 criteria. They also were asked to fulfill a validated questionnaire about life habits and health status. Sperm concentration and percentage of motile sperm were related to socio-demographic data, environmental factors, health status, and life habits, to determine the predictive accuracy of a Multilayer Perceptron Network, a type of Artificial Neural Network. In conclusion, we have developed an Artificial Neural Ne...
Bookmarks Related papers MentionsView impact
Complexity, 2019
There is a growing awareness that the complexity of managing Big Data is one of the main challeng... more There is a growing awareness that the complexity of managing Big Data is one of the main challenges in the developing field of the Internet of Things (IoT). Complexity arises from several aspects of the Big Data life cycle, such as gathering data, storing them onto cloud servers, cleaning and integrating the data, a process involving the last advances in ontologies, such as Extensible Markup Language (XML) and Resource Description Framework (RDF), and the application of machine learning methods to carry out classifications, predictions, and visualizations. In this review, the state of the art of all the aforementioned aspects of Big Data in the context of the Internet of Things is exposed. The most novel technologies in machine learning, deep learning, and data mining on Big Data are discussed as well. Finally, we also point the reader to the state-of-the-art literature for further in-depth studies, and we present the major trends for the future.
Bookmarks Related papers MentionsView impact
Sensors (Basel, Switzerland), Jan 23, 2018
The new sensing applications need enhanced computing capabilities to handle the requirements of c... more The new sensing applications need enhanced computing capabilities to handle the requirements of complex and huge data processing. The Internet of Things (IoT) concept brings processing and communication features to devices. In addition, the Cloud Computing paradigm provides resources and infrastructures for performing the computations and outsourcing the work from the IoT devices. This scenario opens new opportunities for designing advanced IoT-based applications, however, there is still much research to be done to properly gear all the systems for working together. This work proposes a collaborative model and an architecture to take advantage of the available computing resources. The resulting architecture involves a novel network design with different levels which combines sensing and processing capabilities based on the Mobile Cloud Computing (MCC) paradigm. An experiment is included to demonstrate that this approach can be used in diverse real applications. The results show the ...
Bookmarks Related papers MentionsView impact
Applied Soft Computing, 2017
Bookmarks Related papers MentionsView impact
Support Vector Machines Data Analysis Machine Learning and Applications, 2011
Bookmarks Related papers MentionsView impact
Cognitive Systems Research, 2016
Bookmarks Related papers MentionsView impact
Connection Science, 2015
Bookmarks Related papers MentionsView impact
Lecture Notes in Computer Science, 2005
This paper describes a system for haptic object categorization. It consists of a robotic hand, th... more This paper describes a system for haptic object categorization. It consists of a robotic hand, the LUCS Haptic Hand I, together with software modules that to some extent simulate the functioning of the primary and the secondary somatosensory cortices. The haptic system is the first one in a project at LUCS aiming at studying haptic perception. In the project, several robotic hands together with cognitive computational models of the corresponding human neurophysiological systems will be built. The haptic system was trained and tested with a set of objects consisting of balls and cubes, and the activation in the modules corresponding to secondary somatosensory cortex was studied. The results suggest that the haptic system is capable of categorization of objects according to size, if the shapes of the objects are restricted to spheres and cubes.
Bookmarks Related papers MentionsView impact
The 2011 International Joint Conference on Neural Networks, 2011
ABSTRACT The classical connectionist models are not well suited to working with data varying over... more ABSTRACT The classical connectionist models are not well suited to working with data varying over time. According to this, temporal connectionist models have emerged and constitute a continuously growing research field. In this paper we present a novel supervised recurrent neural network architecture (SARASOM) based on the Associative Self-Organizing Map (A-SOM). The A-SOM is a variant of the Self-Organizing Map (SOM) that develops a representation of its input space as well as learns to associate its activity with an arbitrary number of additional inputs. In this context the A-SOM learns to associate its previous activity with a delay of one iteration. The performance of the SARASOM was evaluated and compared with the Elman network in a number of prediction tasks using sequences of letters (including some experiments with a reduced lexicon of 10 words). The results are very encouraging with SARASOM learning slightly better than the Elman network.
Bookmarks Related papers MentionsView impact
2013 XXIV International Conference on Information, Communication and Automation Technologies (ICAT), 2013
Bookmarks Related papers MentionsView impact
Self Organizing Maps - Applications and Novel Algorithm Design, 2011
Bookmarks Related papers MentionsView impact
Studies in Computational Intelligence, 2011
We present experiments with a multimodal system based on a novel variant of the Self-Organizing M... more We present experiments with a multimodal system based on a novel variant of the Self-Organizing Map (SOM) called the Associative Self-Organizing Map (A-SOM). The A-SOM is similar to the SOM and develops a representation of its input space, but also learns to associate its activity with additional inputs, e.g. the activities of one or several external SOMs. This enables the
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Uploads
Papers by Magnus Johnsson