SOLVING SUDOKU USING ARTIFICIAL NEURAL NETWORKS
DOI:
https://doi.org/10.24867/18BE13BosicKeywords:
Artificial neural networks, cConvolutional neural networks, AdamAbstract
This paper provides an overview of different models of artificial and convolutional neural networks and discusses the advantages of using the Adam optimizer over some other optimization algorithms. Proposed ANN models will be used for solving a Sudoku game. A detailed analysis of data processing before model training is given, and a comparison of the obtained results is made.
References
[1] https://research.google.com/
colaboratory/faq.html
[2] C. M. Teng., ˇCorrecting noisy data”, 16th Internatio-
nal Conf. on Machine Learning 1999.
[3] Isabelle Guyon and André Elisseeff, "An Introducti-
on to Variable and Feature Selection”, JMLR Special
Issue on Variable and Feature Selection 2003.
[4] Khan, Rahmani et al, "A Guide to Convolutional Ne-
ural Networks for Computer Vision”, 2018.
[5] Diederik P. Kingma and Jimmy Lei Ba, "Adam: A
method for stochastic optimization”, Published as a
conference paper at ICLR 2015.
[6] Walter Pitts and Warren McCulloch, "A Logical Cal-
culus of Ideas Immanent in Nervous Activity”, 1943.
[7] Alex Krizhevsky and Ilya Sutskever and Geoffrey E.
Hinton, "ImageNet Classification with Deep Convo-
lutional Neural Networks", 2012.
[8] Harrison Kinsley and Daniel Kukieła, "Neural Ne-
tworks from Scratch in Python", Kinsley Enterprises
Inc. 2020.
[9] Yves Chauvin and David E. Rumelhart, "Backpropa-
gation:Theory, Architectures, and Applications", La-
wrence Erlbaum Associates 1995.
[10] Rumelhart and McClelland and the PDP Research
Group, "Parallel distributed processing: Explorations
in the microstructure of cognition.", 1986
colaboratory/faq.html
[2] C. M. Teng., ˇCorrecting noisy data”, 16th Internatio-
nal Conf. on Machine Learning 1999.
[3] Isabelle Guyon and André Elisseeff, "An Introducti-
on to Variable and Feature Selection”, JMLR Special
Issue on Variable and Feature Selection 2003.
[4] Khan, Rahmani et al, "A Guide to Convolutional Ne-
ural Networks for Computer Vision”, 2018.
[5] Diederik P. Kingma and Jimmy Lei Ba, "Adam: A
method for stochastic optimization”, Published as a
conference paper at ICLR 2015.
[6] Walter Pitts and Warren McCulloch, "A Logical Cal-
culus of Ideas Immanent in Nervous Activity”, 1943.
[7] Alex Krizhevsky and Ilya Sutskever and Geoffrey E.
Hinton, "ImageNet Classification with Deep Convo-
lutional Neural Networks", 2012.
[8] Harrison Kinsley and Daniel Kukieła, "Neural Ne-
tworks from Scratch in Python", Kinsley Enterprises
Inc. 2020.
[9] Yves Chauvin and David E. Rumelhart, "Backpropa-
gation:Theory, Architectures, and Applications", La-
wrence Erlbaum Associates 1995.
[10] Rumelhart and McClelland and the PDP Research
Group, "Parallel distributed processing: Explorations
in the microstructure of cognition.", 1986
Downloads
Published
2022-07-07
Issue
Section
Electrotechnical and Computer Engineering
