Multi-Activation Dendritic Neural Network (MA-DNN) Working Example of Dendritic-Based Artificial Neural Network

Tomov, Konstantin; Momcheva, Galina

doi:10.2478/cait-2023-0030

Abstract

Throughout the years neural networks have been based on the perceptron model of the artificial neuron. Attempts to stray from it are few to none. The perceptron simply works and that has discouraged research around other neuron models. New discoveries highlight the importance of dendrites in the neuron, but the perceptron model does not include them. This brings us to the goal of the paper which is to present and test different models of artificial neurons that utilize dendrites to create an artificial neuron that better represents the biological neuron. The authors propose two models. One is made with the purpose of testing the idea of the dendritic neuron. The distinguishing feature of the second model is that it implements activation functions after its dendrites. Results from the second model suggest that it performs as well as or even better than the perceptron model.

References

N. Spruston, G. Stuart, M. Häusser, G. Stuart, N. Spruston, M. Häusser, Eds. Principles of Dendritic Integration. – In: Dendrites. Oxford, Oxford University Press, 2016, pp. 351-398.
Search in Google Scholar Back to article
Richards, S. E. V., S. D. Van Hooser. Neural Architecture: From Cells to Circuits. – Journal of Neurophysiology, Vol. 120, 2018, No 2, pp. 854-866.
Search in Google Scholar Back to article
Spruston, N. Pyramidal Neurons: Dendritic Structure and Synaptic Integration. – Nat. Rev. Neurosci., Vol. 9, 2008, pp. 206-221.
Search in Google Scholar Back to article
Zhang, J. Basic Neural Units of the Brain: Neurons, Synapses and Action Potential. – arXiv preprint arXiv:1906.01703, 2019.
Search in Google Scholar Back to article
Herculano-Houzel, S. The Remarkable, Yet Not Extraordinary, Human Brain as a Scaled-Up Primate Brain and Its Associated Cost. – Proceedings of the National Academy of Sciences, Vol. 109, 2012, pp. 10661-10668.
Search in Google Scholar Back to article
Chavlis, S., P. Poirazi. Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks. – Current Opinion in Neurobiology, Vol. 70, 2021, pp. 1-10.
Search in Google Scholar Back to article
McCulloch, W. S., W. Pitts. A Logical Calculus of the Ideas Immanent in Nervous Activity. – Bulletin of Mathematical Biophysics, Vol. 5, 1943, pp. 115-133.
Search in Google Scholar Back to article
Rosenblatt, F. The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain. – Psychological Review, Vol. 65, 1958, pp. 386-408.
Search in Google Scholar Back to article
Yanling, Z., D. Bimin, W. Zhanrong. Analysis and Study of Perceptron to Solve XOR Problem. – In: Proc. of 2nd International Workshop on Autonomous Decentralized System, 2002, pp. 168-173.
Search in Google Scholar Back to article
G. Stuart, N. Spruston, M. Häusser, Eds. Dendrites. Oxford, Oxford University Press, 2016.
Search in Google Scholar Back to article
Wang, Z., S. Gao, J. Wang, H. Yang, Y. Todo. A Dendritic Neuron Model with Adaptive Synapses Trained by Differential Evolution Algorithm. – Computational Intelligence and Neuroscience, Vol. e2710561, 2020.
Search in Google Scholar Back to article
Ji, J., S. Gao, J. Cheng, Z. Tang, Y. Todo. An Approximate Logic Neuron Model with a Dendritic Structure. – Neurocomputing, Vol. 173, 2016, pp. 1775-1783.
Search in Google Scholar Back to article
Marcie, J. T., E. von Hippel. The Situated Nature of Adaptive Learning in Organizations. – Organization Science, Vol. 8, 1997, No 1, pp. 71-83.
Search in Google Scholar Back to article
Xiao, H., R. Kashif, V. Roland. Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms. – arXiv preprint arXiv:1708.07747, 2017.
Search in Google Scholar Back to article
Fisher, R. A. The Use of Multiple Measurements in Taxonomic Problems. – Annals of Human Genetics, Vol. 7, 1936, pp. 179-188.
Search in Google Scholar Back to article
Wolberg, W. H., W. N. Street, O. L. Mangasarian. Breast Cancer Wisconsin (Diagnostic) Data Set. – UCI Machine Learning Repository, 1992.
Search in Google Scholar Back to article
Krizhevsky, A., G. Hinton. Learning Multiple Layers of Features from Tiny Images. – University of Toronto, 2009.
Search in Google Scholar Back to article
Don, S., D. Chung, K. Revathy, E. Choi, D. Min. A New Approach for Mammogram Image Classification Using Fractal Properties. – Cybernetics and Information Technologies, Vol. 12, 2013, No 2, pp. 69-83.
Search in Google Scholar Back to article

Multi-Activation Dendritic Neural Network (MA-DNN) Working Example of Dendritic-Based Artificial Neural Network

Abstract

Paradigm

My account