Improve Research Reproducibility A Bio-protocol resource
Concise Method
tooltip

Neural network characteristics

DV Dániel Varga
SS Szilárd Szikora
TN Tibor Novák
GP Gergely Pap
GL Gábor Lékó
JM József Mihály
ME Miklós Erdélyi
request Request a Protocol
ask Ask a question
Favorite

The Artificial Neural Network (ANN) used for the classification of the data points contained one hidden layer with 32 units using the ReLU activation function as non-linearity. The loss function was binary cross-entropy with a single sigmoid output neuron. Adam was used as an optimizer. The model was trained for 10 epochs with a batch size of 32. Implementation and training was completed in ‘keras 2.2.4’ using a consumer grade Intel Core i7-6700K CPU without utilizing any GPU. With such a setup training takes less than a day. Classification roughly scales with N*log(N) on large datasets, bounded by the k-nearest neighbor algorithm. The classification of a single double-line structure takes around one minute on a regular dataset, while the object detection of a dataset contaning ∼20 doubleline structures requires less than a minute.

Copyright and License information: The Author(s) ©2023
Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A