Artificial neural networks in the science and education context
Abstract
The increasing popularity of artificial neural networks (ANNs) in education, science, and commerce may give the impression of a revolution that has taken place in computer modeling and optimization algorithms. This short review highlights the fundamental shortcomings of ANNs and the potential harm that can be caused by encouraging the study of ANNs to the detriment of strict mathematical methods.
References
1. B. Widrow. An Adaptive “Adaline” Neuron Using Chemical “Memistors”. TR No. 1553-2, Stanford University, California, USA (1960). URL: http://www-isl.stanford.edu/~widrow/papers/t1960anadaptive.pdf
2. F. Rosenblatt. Perceptron Simulation Experiments. Proceedings of the IRE, 48(3), 301-309 (1960).
3. J. Nickolls, I. Buck, M. Garland, K. Skadron. Scalable Parallel Programming with CUDA. Queue - GPU Computing, 6(2), 40-53 (2008)
4. G. E. Hinton, S. Osindero, Y. Teh. A fast learning algorithm for deep belief nets. Neural Computation, 18, 1527-1554 (2006)
5. G. E. Hinton, R. R. Salakhutdinov Reducing the dimensionality of data with neural networks.
Science, 313, 504 - 507 (2006)
6. D.H. Wolpert, W.G. Macready. No Free Lunch Theorems for Search, Technical Report SFI-TR-95-02-010, Santa Fe Institute, USA (1995)
7. C. Rackauckas. Algorithm efficiency comes from problem information (2018). URL: http://www.stochasticlifestyle.com/algorithm-efficiency-comes-problem-information/
8. N. Golyandina, A. Korobeynikov, A. Shlemov, K. Usevich. Multivariate and 2D Extensions of Singular Spectrum Analysis with the Rssa Package. Journal of Statistical Software, 67(2), 1-78 (2015)
9. K. H. Jin, J. C. Ye. Annihilating Filter-Based Low-Rank Hankel Matrix Approach for Image Inpainting. IEEE Transactions on Image Processing, 24(11), 3498-3511 (2015)
10. T. Simonite. AI Has a Hallucination Problem that’s Proving Hard to Fix. WIRED (2018). URL: https://www.wired.com/story/ai-has-a-hallucination-problem-thats-proving-tough-to-fix/
11. J. Su, D. V. Vargas, S. Kouichi. One pixel attack for fooling deep neural networks (2017). URL: http://arxiv.org/pdf/1710.08864
12. D. Silver et al. Mastering the game of Go without human knowledge. Nature, 550, 354-359 (2017)
13. D. Silver et al. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017). URL: http://arxiv.org/pdf/1712.01815
14. J. C. Collados. Is AlphaZero really a scientific breakthrough in AI? Medium (2017). URL: https://medium.com/@josecamachocollados/is-alphazero-really-a-scientific-breakthrough-in-ai-bf66ae1c84f2
15. S. Kuindersma et al. Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot. Autonomous Robots, 40(3), 429-455 (2016).
16. C. J. Shallue, A. Vanderburg. Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90 (2017). URL: http://arxiv.org/pdf/1712.05044
17. E. A. Smirnov, A. B. Markov. Identification of asteroids trapped inside three-body mean motion resonances: a machine-learning approach. Monthly Notices of the Royal Astronomical Society, 469(2), 2024–2031 (2017).
18. R. Epstein. The empty brain. Aeon (2016). URL: https://aeon.co/essays/your-brain-does-not-process-information-and-it-is-not-a-computer
19. H. Markram et al. Reconstruction and Simulation of Neocortical Microcircuitry. Cell, 163(2), 456-492 (2015)
20. B. Szigeti. OpenWorm: an open-science approach to modeling Caenorhabditis elegans. Frontiers in Computational Neuroscience, 137 (2014)
2. F. Rosenblatt. Perceptron Simulation Experiments. Proceedings of the IRE, 48(3), 301-309 (1960).
3. J. Nickolls, I. Buck, M. Garland, K. Skadron. Scalable Parallel Programming with CUDA. Queue - GPU Computing, 6(2), 40-53 (2008)
4. G. E. Hinton, S. Osindero, Y. Teh. A fast learning algorithm for deep belief nets. Neural Computation, 18, 1527-1554 (2006)
5. G. E. Hinton, R. R. Salakhutdinov Reducing the dimensionality of data with neural networks.
Science, 313, 504 - 507 (2006)
6. D.H. Wolpert, W.G. Macready. No Free Lunch Theorems for Search, Technical Report SFI-TR-95-02-010, Santa Fe Institute, USA (1995)
7. C. Rackauckas. Algorithm efficiency comes from problem information (2018). URL: http://www.stochasticlifestyle.com/algorithm-efficiency-comes-problem-information/
8. N. Golyandina, A. Korobeynikov, A. Shlemov, K. Usevich. Multivariate and 2D Extensions of Singular Spectrum Analysis with the Rssa Package. Journal of Statistical Software, 67(2), 1-78 (2015)
9. K. H. Jin, J. C. Ye. Annihilating Filter-Based Low-Rank Hankel Matrix Approach for Image Inpainting. IEEE Transactions on Image Processing, 24(11), 3498-3511 (2015)
10. T. Simonite. AI Has a Hallucination Problem that’s Proving Hard to Fix. WIRED (2018). URL: https://www.wired.com/story/ai-has-a-hallucination-problem-thats-proving-tough-to-fix/
11. J. Su, D. V. Vargas, S. Kouichi. One pixel attack for fooling deep neural networks (2017). URL: http://arxiv.org/pdf/1710.08864
12. D. Silver et al. Mastering the game of Go without human knowledge. Nature, 550, 354-359 (2017)
13. D. Silver et al. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017). URL: http://arxiv.org/pdf/1712.01815
14. J. C. Collados. Is AlphaZero really a scientific breakthrough in AI? Medium (2017). URL: https://medium.com/@josecamachocollados/is-alphazero-really-a-scientific-breakthrough-in-ai-bf66ae1c84f2
15. S. Kuindersma et al. Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot. Autonomous Robots, 40(3), 429-455 (2016).
16. C. J. Shallue, A. Vanderburg. Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90 (2017). URL: http://arxiv.org/pdf/1712.05044
17. E. A. Smirnov, A. B. Markov. Identification of asteroids trapped inside three-body mean motion resonances: a machine-learning approach. Monthly Notices of the Royal Astronomical Society, 469(2), 2024–2031 (2017).
18. R. Epstein. The empty brain. Aeon (2016). URL: https://aeon.co/essays/your-brain-does-not-process-information-and-it-is-not-a-computer
19. H. Markram et al. Reconstruction and Simulation of Neocortical Microcircuitry. Cell, 163(2), 456-492 (2015)
20. B. Szigeti. OpenWorm: an open-science approach to modeling Caenorhabditis elegans. Frontiers in Computational Neuroscience, 137 (2014)
Published
2017-12-30
How to Cite
Павлов, Д. А. (2017). Artificial neural networks in the science and education context. Computer Tools in Education, (6), 25-31. Retrieved from http://cte.eltech.ru/ojs/index.php/kio/article/view/1506
Issue
Section
Computer science
This work is licensed under a Creative Commons Attribution 4.0 International License.
