Do biological synapses perform probabilistic computations?

Peláez, Javier Ropero; Andina, Diego

doi:10.1016/j.neucom.2012.08.042

Cited by 22 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Intrinsic plasticity adjusts the global excitability of the neuron so that highly excited neurons will be less excitable in the future, and vice versa. In this paper, we continue the research started in previous works [3,4,[14][15][16][17]. Here we use KLN networks to classify the patterns in the Wisconsin Breast Cancer Database (WBCD) [19].…”

Section: Introductionmentioning

confidence: 93%

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

Fombellida

Ropero-Peláez

Andina

2017

Biomedical Applications Based on Natural and Artificial Computing

View full text Add to dashboard Cite

Abstract. 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-ofthe-art research: the diagnosis of breast cancer data from the Wisconsin Breast Cancer Database.

show abstract

Section: Introductionmentioning

confidence: 93%

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

Fombellida

Ropero-Peláez

Andina

2017

Biomedical Applications Based on Natural and Artificial Computing

View full text Add to dashboard Cite

show abstract

“…In this case study, we progress on previous works [1,[21][22][23]. In them, metaplasticity, a basic property of biological neuron connections that neuroscientists believe crucial in achieving the biological learning, is modeled as artificial metaplasticity.…”

Section: Potential Of Bioinspired Systems and The Case Of Automated Cmentioning

confidence: 99%

“…Artificial neural networks (ANNs), widely used in pattern classification, are biologically inspired distributed parallel processing networks based on the neuron organization and decision-making process of the human brain [22].…”

Section: Artificial Metaplasticity Neural Network Modelmentioning

confidence: 99%

“…The concept of biological metaplasticity was defined in 1996 by Abraham [26] and now is widely applied in the fields of biology, finances, neuroscience, physiology, neurology and others [26,27]. Recently, Andina [21], Ropero-Peláez [22] and Marcano-Cerdeño [28] have introduced and modeled the biological property metaplasticity in the field of ANNs, obtaining excellent results.…”

Section: Artificial Metaplasticity Neural Network Modelmentioning

confidence: 99%

See 1 more Smart Citation

Tackling business intelligence with bioinspired deep learning

Fombellida

Martín‐Rubio

Torres-Alegre

et al. 2018

Neural Comput & Applic

View full text Add to dashboard Cite

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.

show abstract

“…A Equação (9) calcula o deslocamento da função de ativação, s no tempo t, em termos do deslocamento e da probabilidade de saída do neurônio no tempo t-1 (PELÁEZ; ANDINA, 2013 sendo υ um fator arbitrário pequeno que ajusta a velocidade de deslocamento da função de ativação. Quando os neurônios são altamente ativados, a tendência do fator de deslocamento, s, é aumentar, deslocando assim a função de ativação para a direita.…”

Section: Gaba-unclassified

Modelo neurocomputacional dos estágios iniciais da doença de Alzheimer

Aguiar-Furucho¹

View full text Add to dashboard Cite

Do biological synapses perform probabilistic computations?

Cited by 22 publications

References 16 publications

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

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

Tackling business intelligence with bioinspired deep learning

Modelo neurocomputacional dos estágios iniciais da doença de Alzheimer

Contact Info

Product

Resources

About