Influence of Training Set Selection in Artificial Neural Network-Based Propagation Path Loss Predictions

This paper analyzes the use of artificial neural networks (ANNs) for predicting the received power/path loss in both outdoor and indoor links. The approach followed has been a combined use of ANNs and ray-tracing, the latter allowing the identification and parameterization of the so-called dominant path. A complete description of the process for creating and training an ANN-based model is presented with special emphasis on the training process. More specifically, we will be discussing various techniques to arrive at valid predictions focusing on an optimum selection of the training set. A quantitative analysis based on results from two narrowband measurement campaigns, one outdoors and the other indoors, is also presented.

Classification of neocortical interneurons using affinity propagation

In spite of over a century of research on cortical circuits, it is still unknown how many classes of cortical neurons exist. Neuronal classification has been a difficult problem because it is unclear what a neuronal cell class actually is and what are the best characteristics are to define them. Recently, unsupervised classifications using cluster analysis based on morphological, physiological or molecular characteristics, when applied to selected datasets, have provided quantitative and unbiased identification of distinct neuronal subtypes. However, better and more robust classification methods are needed for increasingly complex and larger datasets. We explored the use of affinity propagation, a recently developed unsupervised classification algorithm imported from machine learning, which gives a representative example or exemplar for each cluster. As a case study, we applied affinity propagation to a test dataset of 337 interneurons belonging to four subtypes, previously identified based on morphological and physiological characteristics. We found that affinity propagation correctly classified most of the neurons in a blind, non-supervised manner. In fact, using a combined anatomical/physiological dataset, our algorithm differentiated parvalbumin from somatostatin interneurons in 49 out of 50 cases. Affinity propagation could therefore be used in future studies to validly classify neurons, as a first step to help reverse engineer neural circuits.

The propagation of nerve pulses: From the Hodgkin-Huxley model to the soliton theory

The present project aims to describe and study the nature and transmission of nerve pulses. First we review a classical model by Hodgkin-Huxley which describes the nerve pulse as a pure electric signal which propagates due to the opening of some time- and voltage-dependent ion channels. Although this model was quite successful when introduced, it fails to provide a satisfactory explanation to other phenomena that occur in the transmission of nerve pulses, therefore a new theory seems to be necessary. The soliton theory is one such theory, which we explain after introducing two topics that are important for its understanding: (i) the lipid melting of membranes, which are found to display nonlinearity and dispersion during the melting transition, and (ii) the discovery and the conditions required for the existence of solitons. In the soliton theory, the pulse is presented as an electromechanical soliton which forces the membrane through the transition while propagating. The action of anesthesia is also explained in the new framework by the melting point depression caused by anesthetics. Finally, we present a comparison between the two models.