Information-theoretic multi-layered supervised self-organizing maps for improved prediction performance and explicit internal representation

2014 ◽  
Author(s):  
Ryotaro Kamimura
Keyword(s):  
Internal Representation ◽  
Prediction Performance ◽  
Self Organizing Maps ◽  
Information Theoretic ◽  
Self Organizing

scholarly journals Cooperation-Controlled Learning for Explicit Class Structure in Self-Organizing Maps

2014 ◽  
Vol 2014 ◽  
pp. 1-24 ◽  
Author(s):  
Ryotaro Kamimura
Keyword(s):  
Cooperative Networks ◽  
Class Structure ◽  
Small Individual ◽  
Self Organizing Maps ◽  
Information Theoretic ◽  
New Type ◽  
Points Of View ◽  
Information Theoretic Method ◽  
Self Organizing

We attempt to demonstrate the effectiveness of multiple points of view toward neural networks. By restricting ourselves to two points of view of a neuron, we propose a new type of information-theoretic method called “cooperation-controlled learning.” In this method, individual and collective neurons are distinguished from one another, and we suppose that the characteristics of individual and collective neurons are different. To implement individual and collective neurons, we prepare two networks, namely, cooperative and uncooperative networks. The roles of these networks and the roles of individual and collective neurons are controlled by the cooperation parameter. As the parameter is increased, the role of cooperative networks becomes more important in learning, and the characteristics of collective neurons become more dominant. On the other hand, when the parameter is small, individual neurons play a more important role. We applied the method to the automobile and housing data from the machine learning database and examined whether explicit class boundaries could be obtained. Experimental results showed that cooperation-controlled learning, in particular taking into account information on input units, could be used to produce clearer class structure than conventional self-organizing maps.

scholarly journals Predicting Protein-Ligand Binding Site for Drug Design Using Context Relevant Self Organizing Maps (CRSOM)

2020 ◽  
Vol 13 (6) ◽  
pp. 11-19
Author(s):  
Elly Imah ◽  
◽  
Antri Wulandari ◽  
Keyword(s):  
Drug Design ◽  
Ligand Binding ◽  
Binding Site ◽  
Binding Sites ◽  
Binary Classification ◽  
Internal Representation ◽  
Test Time ◽  
Learning Context ◽  
Self Organizing Maps ◽  
Self Organizing

Research on binding sites has been done to find suitable ligands to treat a particular disease. The binding site is a pocket on the surface of the protein, which acts as a place to attach a ligand. In bioinformatics, searching for binding sites is applied to drug design problems. Currently, computer-aided drug design has been developed. In this study, the prediction of protein-ligand binding sites formulated as a binary classification, which is distinguish the location that has potential to binding the ligand and the location that has no potential to binding the ligand. The dataset that will be used in this research is taken from the RCSB Protein Data Bank of 14 proteins data. The classification method used in this research is Context Relevant Self Organizing Maps (CRSOM), where the CRSOM method gives higher accuracy results compared to Backpropagation and Deep Learning. Context Relevant Self Organizing Maps (CRSOM) is chosen as a supervised learning classification algorithm that has an optimal internal representation, where data belonging different classes are separated with wider margin, while data belonging to the same class are clustered closely to each other. Thus, CRSOM is able to visualize high-dimensional protein data into binding site and non-binding site classes significantly. The results of the study obtained an average training accuracy of 99,60%, testing accuracy of 96.26%, and the average test time of 28.63 seconds, the result is better than the predecessor.

scholarly journals Brain-Inspired Self-Organization with Cellular Neuromorphic Computing for Multimodal Unsupervised Learning

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1605 ◽  
Author(s):  
Lyes Khacef ◽  
Laurent Rodriguez ◽  
Benoît Miramond
Keyword(s):  
Unsupervised Learning ◽  
Cortical Plasticity ◽  
Internal Representation ◽  
Neural System ◽  
Self Organization ◽  
Self Organizing Map ◽  
Self Organizing Maps ◽  
Dynamic Vision ◽  
Neuromorphic Architecture ◽  
Self Organizing

Cortical plasticity is one of the main features that enable our ability to learn and adapt in our environment. Indeed, the cerebral cortex self-organizes itself through structural and synaptic plasticity mechanisms that are very likely at the basis of an extremely interesting characteristic of the human brain development: the multimodal association. In spite of the diversity of the sensory modalities, like sight, sound and touch, the brain arrives at the same concepts (convergence). Moreover, biological observations show that one modality can activate the internal representation of another modality when both are correlated (divergence). In this work, we propose the Reentrant Self-Organizing Map (ReSOM), a brain-inspired neural system based on the reentry theory using Self-Organizing Maps and Hebbian-like learning. We propose and compare different computational methods for unsupervised learning and inference, then quantify the gain of the ReSOM in a multimodal classification task. The divergence mechanism is used to label one modality based on the other, while the convergence mechanism is used to improve the overall accuracy of the system. We perform our experiments on a constructed written/spoken digits database and a Dynamic Vision Sensor (DVS)/EletroMyoGraphy (EMG) hand gestures database. The proposed model is implemented on a cellular neuromorphic architecture that enables distributed computing with local connectivity. We show the gain of the so-called hardware plasticity induced by the ReSOM, where the system’s topology is not fixed by the user but learned along the system’s experience through self-organization.

Sign in / Sign up

Export Citation Format

Share Document