Juan Fombellida

Artificial Metaplasticity can Improve Artificial Neural Networks Learning

Abstract Metaplasticity property of biological synapses is interpreted in this paper as the concept of placing greater emphasis on training patterns that are less frequent. A novel implementation is proposed in which, during the network learning phase, a priority is given to weight updating of less frequent activations over the more frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested on the Multilayer Perceptron type network with Backpropagation training. The results obtained for the chosen application show a much more efficient training, while at least maintaining the Multilayer Perceptron performance.

Swarm architectures for Ground-based Air Defense Systems of Systems

New generations of Ground based Air Defense Systems of Systems used in modernized Armed Forces maintain the architectures used in their previous versions, constrained by hierarchical radio communications and centralized Command and Control restrictions. Current state-of-the-art technology in these areas allows a refocusing of these architectures towards a swarm approach. Advantages in terms of effectiveness, scalability and survivability are identified, and a preliminary set of swarm algorithms are proposed and analyzed. Upgrades of these preliminary algorithms are proposed as future research areas.

Artificial Metaplasticity for Deep Learning: Application to WBCD Breast Cancer Database Classification

Deep Learning is a new area of Machine Learning research that deals with learning different levels of representation and abstraction in order to move Machine Learning closer to Artificial Intelligence. Artificial Metaplasticity are Artificial Learning Algorithms based on modelling higher level properties of biological plasticity: the plasticity of plasticity itself, so called Biological Metaplasticity. Artificial Metaplasticity aims to obtain general improvements in Machine Learning based on the experts generally accepted hypothesis that the Metaplasticity of neurons in Biological Brains is of high relevance in Biological Learning. This paper presents and discuss the results of applying different Artificial Metaplasticity implementations in Multilayer Perceptrons at artificial neuron learning level. To illustrate their potential, a relevant application that is the objective of state-of-the-art research has been chosen: the diagnosis of breast cancer data from the Wisconsin Breast Cancer Database. It then concludes that Artificial Metaplasticity also may play a high relevant role in Deep Learning.

Tackling business intelligence with bioinspired deep learning

To tackle the complex problem of providing business intelligence solutions based on business data, bioinspired deep learning has to be considered. This paper focuses on the application of artificial metaplasticity learning in business intelligence systems as an alternative paradigm of achieving a deeper information extraction and learning from arbitrary size data sets. As a case study, artificial metaplasticity multilayer perceptron applied to the automation of credit approval decision based on collected client data is analyzed, showing its potential and improvements over the state-of-the-art techniques. This paper successfully introduces the relevant novelty that the artificial neural network itself estimates the pdf of the input data to be used in the metaplasticity learning, so it is much closer to the biologic reality than previous implementations of artificial metaplasticity.

Artificial Metaplasticity: Application to MIT-BIH Arrhythmias Database

Artificial Metaplasticity are Artificial Learning Algorithms based on modelling higher level properties of biological plasticity: the plasticity of plasticity itself, so called Biological Metaplasticity. Artificial Metaplasticity aims to obtain general improvements in Machine Learning based on the experts generally accepted hypothesis that the Metaplasticity of neurons in Biological Brains is of high relevance in Biological Learning. Artificial Metaplasticity Multilayer Perceptron (AMMLP) is the application of Metaplasticity in MLPs ANNs trying to improve uniform plasticity of the Backpropagation algorithm. In this paper two different AMMLP algorithms are applied to the MIT-BIH electro cardiograms database and results are compared in terms of network performance and error evolution.

Combining edge detection algorithms in intensity SAR images

Edge-detection algorithms are applied to SAR images in order to generate different edge strength maps. The results obtained can be combined to improve the final output in order to get a more defined edge strength map. In this paper different combinations of methods are implemented and evaluated using a criterion based on the quality of the detected edges over the original image. The aspects considered are the false alarm rate, edge thickness and discontinuities inside the detected edges. The results obtained with the edge enhancement techniques are compared and conclusions about the best combination strategies are extracted.

Cooperation and competition based on free market in swarm system architectures for air defense

Algorithms to perform distributed Command and Control functions in Ground based Air Defense Systems of Systems are presented and analyzed. In previous research we presented the benefits of using swarm architectures for this type of application in terms of no single point of failure, lower detectability and higher scalability. Here we propose some Free Market distributed algorithms based on the principles of negotiation and competition among the swarm of agents performing air defense missions. In our research, parameter optimization as well as experimental results in tactical scenarios are obtained through simulation.

AMSOM: artificial metaplasticity in SOM neural networks—application to MIT-BIH arrhythmias database

AbstractArtificial metaplasticity is the machine learning algorithm inspired in the biological metaplasticity of neural synapses. Metaplasticity stands for plasticity of plasticity, and as long as plasticity is related to memory, metaplasticity is related to learning. Implemented in supervised learning assuming input patterns distribution or a related function, it has proved to be very efficient in performance and in training convergence for multidisciplinary applications. Now, for the first time, this kind of artificial metaplasticity is implemented in an unsupervised neural network, achieving also excellent results that are presented in this paper. To compare results, a modified self-organization map is applied to the classification of MIT-BIH cardiac arrhythmias database.

KLN, a new biological koniocortex based unsupervised neural network: competitive results on credit scoring

Koniocortex-Like Network (KLN) model is a Bio-Inspired Neural Network structure that tries to replicate the architecture and properties of the biological koniocortex section of the brain. Based on its biological counterpart that behaves as a Winner-Take-All competitive system, this new structure is composed by different kind of artificial neurons that interplay naturally between them to create a model able to map autonomously the intrinsic knowledge included in a dataset into different classes. Biological properties of the human neural system as metaplasticity and intrinsic plasticity have been translated into this artificial model to create a self-organizing system applicable to multiple disciplines. This approach leads to a natural evolution of the network’s dynamics until obtaining the desired results. The KLN has been previously tested on several synthetic and real datasets, in this article we check its capability to deal with a different type of information by applying it to credit scoring problem, in particular to the classification of credit data from the Australian Credit Approval Database.

Koniocortex-Like Network Unsupervised Learning Surpasses Supervised Results on WBCD Breast Cancer Database

Koniocortex-Like Network is a novel category of Bio-Inspired Neural Networks whose architecture and properties are inspired in the biological koniocortex, the first layer of the cortex that receives information from the thalamus. In the Koniocortex-Like Network competition and pattern classification emerges naturally due to the interplay of inhibitory interneurons, metaplasticity and intrinsic plasticity. Recently proposed, it has shown a big potential for complex tasks with unsupervised learning. Now for the first time, its competitive results are proved in a relevant standard real application that is the objective of state-of-the-art research: the diagnosis of breast cancer data from the Wisconsin Breast Cancer Database.