An evolutionary niche for quantitative theoretical analyses?

2006 ◽  
Vol 29 (1) ◽  
pp. 23-23
Author(s):  
Yasser Roudi ◽  
Alessandro Treves
Keyword(s):  
Neural Networks ◽  
Brain Evolution ◽  
Comparative Neuroanatomy ◽  
Process Information ◽  
Network Analyses ◽  
Theoretical Analyses ◽  
Insight Into

Striedter's book offers precious insight into the comparative neuroanatomy of vertebrate brains, but it stops short of addressing what their evolution is all about: how effectively neural networks process information important for survival. To understand the principles of brain evolution, neuroanatomy needs to be combined not only with genetics, neurophysiology, and ethology, but also with quantitative network analyses.

scholarly journals Reflections on the Constraints and Opportunities in Therapy in Rett Syndrome

2006 ◽  
Vol 6 ◽  
pp. 992-997 ◽  
Author(s):  
Alison M. Kerr
Keyword(s):  
Quality Of Life ◽  
Neural Networks ◽  
Rett Syndrome ◽  
Clear Understanding ◽  
Research Experience ◽  
Hormonal Responses ◽  
Physical Limitations ◽  
The Brain ◽  
Insight Into

More than 20 years of clinical and research experience with affected people in the British Isles has provided insight into particular challenges for therapists, educators, or parents wishing to facilitate learning and to support the development of skills in people with Rett syndrome. This paper considers the challenges in two groups: those due to constraints imposed by the disabilities associated with the disorder and those stemming from the opportunities, often masked by the disorder, allowing the development of skills that depend on less-affected areas of the brain. Because the disorder interferes with the synaptic links between neurones, the functions of the brain that are most dependent on complex neural networks are the most profoundly affected. These functions include speech, memory, learning, generation of ideas, and the planning of fine movements, especially those of the hands. In contrast, spontaneous emotional and hormonal responses appear relatively intact. Whereas failure to appreciate the physical limitations of the disease leads to frustration for therapist and client alike, a clear understanding of the better-preserved areas of competence offers avenues for real progress in learning, the building of satisfying relationships, and achievement of a quality of life.

scholarly journals Semiotic Aggregation in Deep Learning

Entropy ◽  
2020 ◽  
Vol 22 (12) ◽  
pp. 1365
Author(s):  
Bogdan Muşat ◽  
Răzvan Andonie
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Decision Model ◽  
Deep Neural Networks ◽  
Neural Model ◽  
Network Layers ◽  
Saliency Maps ◽  
Spatial Entropy ◽  
Insight Into

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In our experiments, we visualize the superization process and show how the obtained knowledge can be used to explain the neural decision model. In addition, we attempt to optimize the architecture of the neural model employing a semiotic greedy technique. To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.

scholarly journals FIND: Identifying Functionally and Structurally Important Features in Protein Sequences with Deep Neural Networks

2019 ◽  
Author(s):  
Ranjani Murali ◽  
James Hemp ◽  
Victoria Orphan ◽  
Yonatan Bisk
Keyword(s):  
Neural Networks ◽  
Amino Acid ◽  
Hidden Markov Models ◽  
Markov Models ◽  
Genomic Sequence ◽  
Hidden Markov ◽  
Amino Acid Sequences ◽  
Homologous Proteins ◽  
Biological Studies ◽  
Insight Into

AbstractThe ability to correctly predict the functional role of proteins from their amino acid sequences would significantly advance biological studies at the molecular level by improving our ability to understand the biochemical capability of biological organisms from their genomic sequence. Existing methods that are geared towards protein function prediction or annotation mostly use alignment-based approaches and probabilistic models such as Hidden-Markov Models. In this work we introduce a deep learning architecture (FunctionIdentification withNeuralDescriptions orFIND) which performs protein annotation from primary sequence. The accuracy of our methods matches state of the art techniques, such as protein classifiers based on Hidden Markov Models. Further, our approach allows for model introspection via a neural attention mechanism, which weights parts of the amino acid sequence proportionally to their relevance for functional assignment. In this way, the attention weights automatically uncover structurally and functionally relevant features of the classified protein and find novel functional motifs in previously uncharacterized proteins. While this model is applicable to any database of proteins, we chose to apply this model to superfamilies of homologous proteins, with the aim of extracting features inherent to divergent protein families within a larger superfamily. This provided insight into the functional diversification of an enzyme superfamily and its adaptation to different physiological contexts. We tested our approach on three families (nitrogenases, cytochromebd-type oxygen reductases and heme-copper oxygen reductases) and present a detailed analysis of the sequence characteristics identified in previously characterized proteins in the heme-copper oxygen reductase (HCO) superfamily. These are correlated with their catalytic relevance and evolutionary history. FIND was then applied to discover features in previously uncharacterized members of the HCO superfamily, providing insight into their unique sequence features. This modeling approach demonstrates the power of neural networks to recognize patterns in large datasets and can be utilized to discover biochemically and structurally important features in proteins from their amino acid sequences.Author summary

scholarly journals Exploring genetic programming systems with MAP-Elites

2018 ◽  
Author(s):  
Emily Dolson ◽  
Alexander Lalejini ◽  
Charles Ofria
Keyword(s):  
Neural Networks ◽  
Genetic Programming ◽  
Pareto Front ◽  
Underlying Structure ◽  
Phenotypic Traits ◽  
Computation Technique ◽  
Phenotype Space ◽  
Programming Systems ◽  
Insight Into ◽  
Connection Cost

MAP-Elites is an evolutionary computation technique that has proven valuable for exploring and illuminating the genotype-phenotype space of a computational problem. In MAP-Elites, a population is structured based on phenotypic traits of prospective solutions; each cell represents a distinct combination of traits and maintains only the most fit organism found with those traits. The resulting map of trait combinations allows the user to develop a better understanding of how each trait relates to fitness and how traits interact. While MAP-Elites has not been demonstrated to be competitive for identifying the optimal Pareto front, the insights it provides do allow users to better understand the underlying problem. In particular, MAP-Elites has provided insight into the underlying structure of problem representations, such as the value of connection cost or modularity to evolving neural networks. Here, we extend the use of MAP-Elites to examine genetic programming representations, using aspects of program architecture as traits to explore. We demonstrate that MAP-Elites can generate programs with a much wider range of architectures than other evolutionary algorithms do (even those that are highly successful at maintaining diversity), which is not surprising as this is the purpose of MAP-Elites. Ultimately, we propose that MAP-Elites is a useful tool for understanding why genetic programming representations succeed or fail and we suggest that it should be used to choose selection techniques and tune parameters.

scholarly journals How cells determine the number of polarity sites

eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Jian-geng Chiou ◽  
Kyle D Moran ◽  
Daniel J Lew
Keyword(s):  
Design Principle ◽  
Fundamental Question ◽  
Yeast Cells ◽  
Regulatory Mechanisms ◽  
Saturation Point ◽  
Rho Family Gtpases ◽  
Rho Family ◽  
Theoretical Analyses ◽  
Novel Design ◽  
Insight Into

The diversity of cell morphologies arises, in part, through regulation of cell polarity by Rho-family GTPases. A poorly understood but fundamental question concerns the regulatory mechanisms by which different cells generate different numbers of polarity sites. Mass-conserved activator-substrate (MCAS) models that describe polarity circuits develop multiple initial polarity sites, but then those sites engage in competition, leaving a single winner. Theoretical analyses predicted that competition would slow dramatically as GTPase concentrations at different polarity sites increase towards a 'saturation point', allowing polarity sites to coexist. Here, we test this prediction using budding yeast cells, and confirm that increasing the amount of key polarity proteins results in multiple polarity sites and simultaneous budding. Further, we elucidate a novel design principle whereby cells can switch from competition to equalization among polarity sites. These findings provide insight into how cells with diverse morphologies may determine the number of polarity sites.

Theoretical Analyses of the Universal Approximation Capability of a Class of Higher Order Neural Networks Based on Approximate Identity

2016 ◽  
pp. 1456-1470 ◽  
Author(s):  
Saeed Panahian Fard ◽  
Zarita Zainuddin
Keyword(s):  
Neural Networks ◽  
Approximation Theory ◽  
Special Class ◽  
Higher Order ◽  
Approximate Identity ◽  
Universal Approximation ◽  
Multivariate Functions ◽  
Higher Order Neural Networks ◽  
Approximation Capability ◽  
Theoretical Analyses

One of the most important problems in the theory of approximation functions by means of neural networks is universal approximation capability of neural networks. In this study, we investigate the theoretical analyses of the universal approximation capability of a special class of three layer feedforward higher order neural networks based on the concept of approximate identity in the space of continuous multivariate functions. Moreover, we present theoretical analyses of the universal approximation capability of the networks in the spaces of Lebesgue integrable multivariate functions. The methods used in proving our results are based on the concepts of convolution and epsilon-net. The obtained results can be seen as an attempt towards the development of approximation theory by means of neural networks.

A Survey on Various Applications of Artificial Neural Networks in Selected Fields of Healthcare

2011 ◽  
pp. 20-59
Author(s):  
Wolfgang I. Schollhorn ◽  
Jörg M. Jager
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Neuromuscular Control ◽  
Neural Nets ◽  
Biomedical Signals ◽  
Potential Benefits ◽  
Artificial Neural ◽  
Number Of Publications ◽  
Insight Into ◽  
Profound Insight

This chapter gives an overview of artificial neural networks as instruments for processing miscellaneous biomedical signals. A variety of applications are illustrated in several areas of healthcare. The structure of this chapter is rather oriented on medical fields like cardiology, gynecology, or neuromuscular control than on types of neural nets. Many examples demonstrate how neural nets can support the diagnosis and prediction of diseases. However, their content does not claim completeness due to the enormous amount and exponentially increasing number of publications in this field. Besides the potential benefits for healthcare, some remarks on underlying assumptions are also included as well as problems which may occur while applying artificial neural nets. It is hoped that this review gives profound insight into strengths as well as weaknesses of artificial neural networks as tools for processing biomedical signals.

Sign in / Sign up

Export Citation Format

Share Document