scholarly journals Transformer-based artificial neural networks for the conversion between chemical notations

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Lev Krasnov ◽  
Ivan Khokhlov ◽  
Maxim V. Fedorov ◽  
Sergey Sosnin
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Rapid Development ◽  
Performance Level ◽  
Rule Based ◽  
Development Costs ◽  
Overall Performance ◽  
Artificial Neural

AbstractWe developed a Transformer-based artificial neural approach to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct. The overall performance level of our model is comparable to the rule-based solutions. We proved that the accuracy and speed of computations as well as the robustness of the model allow to use it in production. Our showcase demonstrates that a neural-based solution can facilitate rapid development keeping the required level of accuracy. We believe that our findings will inspire other developers to reduce development costs by replacing complex rule-based solutions with neural-based ones.

Time-to-event analysis with artificial neural networks: An integrated analytical and rule-based study for breast cancer

2008 ◽  
Vol 21 (2-3) ◽  
pp. 414-426 ◽  
Author(s):  
Paulo J.G. Lisboa ◽  
Terence A. Etchells ◽  
Ian H. Jarman ◽  
M.S. Hane Aung ◽  
Sylvie Chabaud ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Event Analysis ◽  
Time To Event ◽  
Rule Based ◽  
Artificial Neural

Integrating artificial neural networks with rule-based expert systems

1994 ◽  
Vol 11 (5) ◽  
pp. 497-507 ◽  
Author(s):  
Youngohc Yoon ◽  
Tor Guimaraes ◽  
George Swales
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Expert Systems ◽  
Rule Based ◽  
Artificial Neural

scholarly journals Jaringan Syaraf Tiruan Untuk Memprediksi Nilai Siswa SMA Menggunakan Backpropagation

2021 ◽  
Vol 4 (2) ◽  
pp. 1-7
Author(s):  
Evan Hikler Damanik ◽  
Eka Irawan ◽  
Fitri Rizki
Keyword(s):  
High School ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Rapid Development ◽  
Processing Data ◽  
The Future ◽  
Artificial Neural ◽  
Exam Scores ◽  
Student Grades

A student's mastery of a subject greatly influences the marking given by the teacher / teacher concerned. The need for instructors or teachers to monitor every value of students who are taught science in their respective fields. With the rapid development of technology, it is very helpful for teachers in knowing or predicting the value that students will get related. This study aims to apply the performance of backpropagation artificial neural networks in predicting the value of students of SMA N 1 Sidamanik with various models and minimizing their errors. In this study the authors used data on student grades from SMA N 1 Sidamanik. In processing data values, the authors use artificial neural networks with backpropagation algorithms as logical steps to predict student National Exam Scores in SMA N 1 Sidamanik. The main problem in this study is the decline in student grades in some subjects, in the future students will experience difficulties in reaching the desired university or high school.

Struct2IUPAC -- Transformer-Based Artificial Neural Network for the Conversion Between Chemical Notations

2021 ◽  
Author(s):  
Lev Krasnov ◽  
Ivan Khokhlov ◽  
Maxim Fedorov ◽  
Sergey Sosnin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Information Exchange ◽  
Rapid Development ◽  
Chemical Information ◽  
Rule Based ◽  
Neural Architecture ◽  
Development Costs ◽  
Artificial Neural ◽  
Accuracy Speed

Providing IUPAC chemical names is necessary for chemical information exchange. We developed a Transformer-based artificial neural architecture to translate between SMILES and IUPAC chemical notations: <i>Struct2IUPAC</i> and <i>IUPAC2Struct</i>. Our models demonstrated the performance that is comparable to rule-based solutions. We proved that both accuracy, speed of computations, and the model's robustness allow us to use it in production. Our showcase demonstrates that a neural-based solution can encourage rapid development keeping the same performance. We believe that our findings will inspire other developers to reduce development costs by replacing complex rule-based solutions with neural-based ones. The demonstration of <i>Struct2IUPAC</i> model is available online on <i>Syntelly</i> platform <i>https://app.syntelly.com/smiles2iupac</i>

Artificial Neural Networks in Rule-based Decision Systems

2007 ◽  
Author(s):  
Alexander Yastrebov ◽  
Stanislaw Gad ◽  
Grzegorz Slon ◽  
Andrzej Kulakowski ◽  
Elena Vinogradova
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Rule Based ◽  
Decision Systems ◽  
Artificial Neural

Struct2IUPAC -- Transformer-Based Artificial Neural Network for the Conversion Between Chemical Notations

2020 ◽  
Author(s):  
Lev Krasnov ◽  
Ivan Khokhlov ◽  
Maxim Fedorov ◽  
Sergey Sosnin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Information Exchange ◽  
Rapid Development ◽  
Chemical Information ◽  
Rule Based ◽  
Neural Architecture ◽  
Development Costs ◽  
Artificial Neural ◽  
Accuracy Speed

Providing IUPAC chemical names is necessary for chemical information exchange. We developed a Transformer-based artificial neural architecture to translate between SMILES and IUPAC chemical notations: <i>Struct2IUPAC</i> and <i>IUPAC2Struct</i>. Our models demonstrated the performance that is comparable to rule-based solutions. We proved that both accuracy, speed of computations, and the model's robustness allow us to use it in production. Our showcase demonstrates that a neural-based solution can encourage rapid development keeping the same performance. We believe that our findings will inspire other developers to reduce development costs by replacing complex rule-based solutions with neural-based ones. The demonstration of <i>Struct2IUPAC</i> model is available online on <i>Syntelly</i> platform <i>https://app.syntelly.com/smiles2iupac</i>

Sign in / Sign up

Export Citation Format

Share Document