Local excitation–inhibition ratio for synfire chain propagation in feed-forward neuronal networks

2017 ◽  
Vol 482 ◽  
pp. 308-316 ◽  
Author(s):  
Xinmeng Guo ◽  
Haitao Yu ◽  
Jiang Wang ◽  
Jing Liu ◽  
Yibin Cao ◽  
...  
Keyword(s):  
Neuronal Networks ◽  
Chain Propagation ◽  
Feed Forward ◽  
Local Excitation ◽  
Inhibition Ratio ◽  
Synfire Chain

scholarly journals Investigating Explanatory Factors of Machine Learning Models for Plant Classification

Plants ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 2674
Author(s):  
Wilfried Wöber ◽  
Lars Mehnen ◽  
Peter Sykacek ◽  
Harald Meimberg
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Gaussian Process ◽  
Beta Vulgaris ◽  
Neuronal Network ◽  
Latent Variable ◽  
Neuronal Networks ◽  
Learning Models ◽  
Feed Forward ◽  
Explanatory Factors

Recent progress in machine learning and deep learning has enabled the implementation of plant and crop detection using systematic inspection of the leaf shapes and other morphological characters for identification systems for precision farming. However, the models used for this approach tend to become black-box models, in the sense that it is difficult to trace characters that are the base for the classification. The interpretability is therefore limited and the explanatory factors may not be based on reasonable visible characters. We investigate the explanatory factors of recent machine learning and deep learning models for plant classification tasks. Based on a Daucus carota and a Beta vulgaris image data set, we implement plant classification models and compare those models by their predictive performance as well as explainability. For comparison we implemented a feed forward convolutional neuronal network as a default model. To evaluate the performance, we trained an unsupervised Bayesian Gaussian process latent variable model as well as a convolutional autoencoder for feature extraction and rely on a support vector machine for classification. The explanatory factors of all models were extracted and analyzed. The experiments show, that feed forward convolutional neuronal networks (98.24% and 96.10% mean accuracy) outperforms the Bayesian Gaussian process latent variable pipeline (92.08% and 94.31% mean accuracy) as well as the convolutional autoenceoder pipeline (92.38% and 93.28% mean accuracy) based approaches in terms of classification accuracy, even though not significant for Beta vulgaris images. Additionally, we found that the neuronal network used biological uninterpretable image regions for the plant classification task. In contrast to that, the unsupervised learning models rely on explainable visual characters. We conclude that supervised convolutional neuronal networks must be used carefully to ensure biological interpretability. We recommend unsupervised machine learning, careful feature investigation, and statistical feature analysis for biological applications.

scholarly journals Using feed-forward networks to infer the activity of feed-back neuronal networks

2010 ◽  
Vol 11 (S1) ◽  
Author(s):  
Xinxian Huang ◽  
Farzan Nadim ◽  
Amitabha Bose
Keyword(s):  
Neuronal Networks ◽  
Feed Forward

scholarly journals How Local Excitation-Inhibition Ratio Impacts the Whole Brain Dynamics

2014 ◽  
Vol 34 (23) ◽  
pp. 7886-7898 ◽  
Author(s):  
G. Deco ◽  
A. Ponce-Alvarez ◽  
P. Hagmann ◽  
G. L. Romani ◽  
D. Mantini ◽  
...  
Keyword(s):  
Brain Dynamics ◽  
Whole Brain ◽  
Local Excitation ◽  
Inhibition Ratio

Inhibitory Feedback Loop Induces Anticipated Synchronization in Neuronal Networks

2014 ◽  
Vol 1 ◽  
pp. 636-639
Author(s):  
Fernanda S. Matias ◽  
Pedro V. Carelli ◽  
Claudio R. Mirasso ◽  
Mauro Copelli
Keyword(s):  
Feedback Loop ◽  
Neuronal Networks ◽  
Inhibitory Feedback
Sign in / Sign up

Export Citation Format

Share Document