Comparison between the neural networks Adaline and Perceptron using the IRIS database
Keywords:
Adaline, Perceptron, Redes NeuraisAbstract
Initially, neural networks were developed with the objective of creating a computational system that models the functioning of the human brain, however they started to be used to solve specific tasks. Adaline and Perceptron are two neural networks that calculate an input function using a set of adaptive weights and a bias, despite their similarities, it is known that the Adaline neural network converges to a result more quickly than the Perceptron neural network. This work was designed as a didactic exercise, in order to present how such conclusions are obtained, using the IRIS database as data for classification and training. Throughout the work, Processing programming language was used to develop neural networks and Python programming language for visual presentation of results. The results found show the database classes that can be linearly separated and those that cannot, the conclusion for the best performance among neural networks is defined by the percentage of correct answers in the data classifications.
Downloads
References
Autor (2020). Redes Neurais. Disponível em: <https://github.com/AllanaCampos/Redes-Neurais> Acesso em: 19 Agosto 2020.
Data Science Academy (2019). Deep Learning Book. Disponível em: <http://www.deeplearningbook.com.br/>. Acesso: 02 Julho 2020.
Dua, D. e Graff, C. (2019). UCI Machine Learning Repository. Irvine, CA: University of California, School of Information and Computer Science. Disponível em: <http://archive.ics.uci.edu/ml>. Acesso: 02 Julho 2020.
Hunter, John. Et al (2020). Matplotlib: Visualization with Python. Disponível em: <https://matplotlib.org>. Acesso: 02 Julho 2020.
Matos, Mateus de. Et al. Implementação de redes neurais perceptron e adaline em ambiente labview. Disponível em: <http://repositorio.roca.utfpr.edu.br/jspui/bitstream/1/10215/1/PG_COELE_2018_1_04.pdf>. Acesso: 02 Julho 2020.
Moreira, Sandro (2018). Rede Neural Perceptron Adaline. Disponível em: <https://medium.com/ensina-ai/rede-neural-perceptron-adaline-8f69dc419d4e> Acesso: 17 Julho 2020.
Python (2020). Pandas. Disponível em: <https://pypi.org/project/pandas/> Consultado em Acesso: 17 Julho 2020.
R. A. Fisher (1936). The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics. 7 (2): 179–188. Disponível em: <http://www.comp.tmu.ac.jp/morbier/R/Fisher-1936-Ann._Eugen.pdf>. Acesso: 25 Julho 2020.
Sharma, Rajesh (2020). SIGGRAPH Now | Hands-on Workshop: Machine Learning and Neural Networks – Lecture 3. Disponível em: <https://www.youtube.com/watch?v=anASnKYImSI&t=1670s>. Acesso: 02 Julho 2020.
Silva, IN da, Danilo Hernane Spatti, e Rogério Andrade Flauzino (2010). Redes neurais artificiais para engenharia e ciências aplicadas. São Paulo: Artliber.
Waskom, Michael (2020). Seaborn. Disponível em: <https://seaborn.pydata.org>. Consultado em Acesso: 17 Julho 2020.