Information representation space in artificial and biological neural networks

Malakhova, K.Y.

Full text «Opticheskii Zhurnal»

Full text on elibrary.ru

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Малахова Е.Ю. Пространство описания зрительной сцены в искусственных и биологических нейронных сетях // Оптический журнал. 2020. Т. 87. № 10. С. 50–58. http://doi.org/10.17586/1023-5086-2020-87-10-50-58

Malakhova E. Yu. Information representation space in artificial and biological neural networks [in Russian] // Opticheskii Zhurnal. 2020. V. 87. № 10. P. 50–58. http://doi.org/10.17586/1023-5086-2020-87-10-50-58

For citation (Journal of Optical Technology):

E. Yu. Malakhova, "Information representation space in artificial and biological neural networks," Journal of Optical Technology. 87(10), 598-603 (2020). https://doi.org/10.1364/JOT.87.000598

Abstract:

Convolutional neural networks are often used as a model of the primate visual system. However, it is often overlooked how a task that the network performs and statistics of the training set affect the representation of information in the latent space of the model. This study demonstrates that the properties of artificial neurons in the first two convolutional layers represent the signal statistics (correlation coefficients R=0.63 and R=0.44), whereas the similarity between the space of the problem and information encoding in hidden layers gradually increases in the final convolutional layers (R=0.35), reaching a value of 0.73 in the fully-connected layers. At the final stages of the processing, a category is encoded using a unique set of features, characterized by no or little overlapping with other categories. Thus, in order to increase similarity between the visual system and its model, it is important to maintain a training set and a problem space of the model coherent to those of a biological organism.

Keywords:

convoluted neural networks, information representation, interpreted deep learning, model of visual system

OCIS codes: 200.4260, 330.4060

References:

1. R. Geirhos, D. H. Janssen, H. H. Schütt, J. Rauber, M. Bethge, and F. A. Wichmann, “Comparing deep neural networks against humans: object recognition when the signal gets weaker,” arXiv:1706.06969 (2017).
2. S. Dodge and L. Karam, “A study and comparison of human and deep learning recognition performance under visual distortions,” arXiv:1705.02498 (2017).
3. B. M. Lake, W. Zaremba, R. Fergus, and T. M. Gureckis, “Deep neural networks predict category typicality ratings for images,” in Proceedings of the 37th Annual Conference of the Cognitive Science Society (2015), pp. 1243–1249.
4. N. Baker, H. Lu, G. Erlikhman, and P. J. Kellman, “Deep convolutional networks do not classify based on global object shape,” PLOS Comput. Biol. 14(12), e1006613 (2018).
5. P. Gangopadhyay and J. Das, “Do primates and deep artificial neural networks perform object categorization in a similar manner?” J. Neurosci. 39(6), 946–948 (2019).
6. E. Watanabe, A. Kitaoka, K. Sakamoto, M. Yasugi, and K. Tanaka, “Illusory motion reproduced by deep neural networks trained for prediction,” Front. Psychol. 9, 345 (2018).
7. R. M. Williams and R. V. Yampolskiy, “Optical illusions images dataset,” arXiv:1810.00415 (2018).
8. C. F. Cadieu, H. Hong, D. L. K. Yamins, N. Pinto, D. Ardila, E. A. Solomon, N. J. Majaj, and J. J. DiCarlo, “Deep neural networks rival the representation of primate IT cortex for core visual object recognition,” PLOS Comput. Biol. 10(12), e1003963 (2014). Research Article Vol. 87, No. 10 / October 2020 / Journal of Optical Technology 603
9. S. R. Kheradpisheh, M. Ghodrati, M. Ganjtabesh, and T. Masquelier, “Deep networks resemble human feed-forward vision in invariant object recognition,” arXiv:1508.03929 (2016).
10. T. C. Kietzmann, P. McClure, and N. Kriegeskorte, “Deep neural networks in computational neuroscience,” bioRxiv:133504 (2017).
11. N. Kriegeskorte, “Deep neural networks: a new framework for modeling biological vision and brain information processing,” Annu. Rev. Vis. Sci. 1(15), 417–446 (2015).
12. Y. Li, J. Yosinski, J. Clune, H. Lipson, and J. E. Hopcroft, “Convergent learning: do different neural networks learn the same representations?” in International Conference on Learning Representation (2016), pp. 196–212.
13. H. B. Barlow, “Summation and inhibition in the frog’s retina,” J. Physiol. 119(1), 69–80 (1953).
14. I. I. Tsukerman, “On conformity of spatial frequency filters of visual analyzer with image statistics,” Biophys. 23(6), 1108–1109 (1978).
15. N. N. Krasil’nikov, Yu. E. Shelepin, and O. I. Krasil’nikova, “Filtering in the human visual system under threshold observation conditions,” J. Opt. Technol. 66(1), 3–10 (1999) [Opt. Zh. 66(1), 3–10 (1999)].
16. T. Gollisch and M. Meister, “Eye smarter than scientists believed: neural computations in circuits of the retina,” Neuron 65(2), 150–164 (2010).
17. Y. Dan, J. J. Atick, and R. C. Reid, “Efficient coding of natural scenes in the lateral geniculate nucleus: experimental test of a computational theory,” J. Neurosci. 16(10), 3351–3362 (1996).
18. B. A. Olshausen and D. J. Field, “Emergence of simple-cell receptive field properties by learning a sparse code for natural images,” Nature 381(6583), 607–609 (1996).
19. A. J. Bell and T. J. Sejnowski, “The ‘independent components’ of natural scenes are edge filters,” Vision Res. 37(23), 3327–3338 (1997).
20. A. Hyvarinen, M. Gutmann, and P. O. Hoyer, “Statistical model of natural stimuli predicts edge-like pooling of spatial frequency channels in V2,” BMC Neurosci. 6(1), 12 (2005).
21. C. F. Cadieu and B. A. Olshausen, “Learning intermediate-level representations of form and motion from natural movies,” Neural Comput. 24(4), 827–866 (2012).
22. C. G. Gross, C. D. Rocha-Miranda, and D. B. Bender, “Visual properties of neurons in inferotemporal cortex of the macaque,” J. Neurophysiol. 35(1), 96–111 (1972).
23. K. Tanaka, “Inferotemporal cortex and object vision,” Annu. Rev. Neurosci. 19(1), 109–139 (1996).
24. G. McCarthy, A. Puce, J. C. Gore, and T. Allison, “Face-specific processing in the human fusiform gyrus,” J. Cognit. Neurosci. 9, 605–610 (1997).
25. N. G. Kanwisher, J. McDermott, and M. M. Chun, “The fusiform face area: a module in human extrastriate cortex specialized for face perception,” J. Neurosci. 17, 4302–4311 (1997).
26. P. E. Downing, Y. Jiang, M. Shuman, and N. Kanwisher, “A cortical area selective for visual processing of the human body,” Science 293, 2470–2473 (2001).
27. R. A. Epstein and N. Kanwisher, “A cortical representation of the local visual environment,” Nature 392, 598–601 (1998).
28. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv:1409.1556 (2015).
29. J. Deng,W. Dong, R. Socher, L. J. Li, K. Li, and L. Fei-Fei, “ImageNet: a large-scale hierarchical image database,” in Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009), pp. 248–255.
30. D. Zhang and G. Lu, “Evaluation of similarity measurement for image retrieval,” in International Conference on Neural Networks and Signal Processing (2003), pp. 928–931.
31. B. A. Olshausen and D. J. Field, “Sparse coding of sensory inputs,” Curr. Opin. Neurobiol. 14(4), 481–487 (2004).
32. A. Hyvärinen, J. Hurri, and P. O. Hoyer, Natural Image Statistics: A Probabilistic Approach to Early Computational Vision (Springer Science & Business Media, Berlin, 2009), pp. 131–150.
33. V. Papyan, Y. Romano, and M. Elad, “Convolutional neural networks analyzed via convolutional sparse coding,” J. Mach. Learn. Res. 18(1), 2887–2938 (2017).
34. X. Glorot, A. Bordes, and Y. Bengio, “Deep sparse rectifier neural networks,” in The Fourteenth International Conference on Artificial Intelligence and Statistics (2011), pp. 315–323.