View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation

Current Biology

Volumn 27, Issue 1, 2017, Pages 62-67

  Leibo, Joel Z ^a   Liao, Qianli ^a   Anselmi, Fabio ^a,c   Freiwald, Winrich A ^a,b   Poggio, Tomaso ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b ROCKEFELLER UNIVERSITY   (United States)

^c ISTITUTO ITALIANO DI TECNOLOGIA   (Italy)

Author keywords

computational neuroscience; face patches; face recognition; Hebbian learning; i theory; invariance; mirror symmetry; Oja's rule; unsupervised learning; ventral stream

Indexed keywords

ANIMAL; BIOLOGICAL MODEL; BRAIN; FACIAL RECOGNITION; HEAD MOVEMENT; LEARNING; MACACA; ORIENTATION; PATTERN RECOGNITION; PHOTOSTIMULATION; PHYSIOLOGY; PROCEDURES; SPATIAL ORIENTATION; VISUAL CORTEX;

ANIMALS; BRAIN; FACIAL RECOGNITION; HEAD MOVEMENTS; LEARNING; MACACA; MODELS, NEUROLOGICAL; ORIENTATION; ORIENTATION, SPATIAL; PATTERN RECOGNITION, VISUAL; PHOTIC STIMULATION; VISUAL CORTEX;

EID: 85007478095     PISSN: 09609822     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.cub.2016.10.015     Document Type: Article

References (44)

1. 1 DiCarlo, J.J., Zoccolan, D., Rust, N.C., How does the brain solve visual object recognition?. Neuron 73 (2012), 415–434.
2. 2 Anselmi, F., Leibo, J.Z., Rosasco, L., Mutch, J., Tacchetti, A., Poggio, T., Unsupervised learning of invariant representations. Theor. Comput. Sci. 633 (2016), 112–121.
3. 3 Serre, T., Oliva, A., Poggio, T., A feedforward architecture accounts for rapid categorization. Proc. Natl. Acad. Sci. USA 104 (2007), 6424–6429.
4. 4 Bart, E., Ullman, S., Class-based feature matching across unrestricted transformations. IEEE Trans. Pattern Anal. Mach. Intell. 30 (2008), 1618–1631.
5. 5 Rolls, E.T., Invariant visual object and face recognition: neural and computational bases, and a model, VisNet. Front. Comput. Neurosci., 6, 2012, 35.
6. 6 Krizhevsky, A., Sutskever, I., and Hinton, G. (2012). ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25 (NIPS 2012), 1106–1114.
7. 7 Freiwald, W.A., Tsao, D.Y., Functional compartmentalization and viewpoint generalization within the macaque face-processing system. Science 330 (2010), 845–851.
8. 8 Tsao, D.Y., Freiwald, W.A., Knutsen, T.A., Mandeville, J.B., Tootell, R.B., Faces and objects in macaque cerebral cortex. Nat. Neurosci. 6 (2003), 989–995.
9. 9 Tsao, D.Y., Freiwald, W.A., Tootell, R.B., Livingstone, M.S., A cortical region consisting entirely of face-selective cells. Science 311 (2006), 670–674.
10. 10 Ku, S.P., Tolias, A.S., Logothetis, N.K., Goense, J., fMRI of the face-processing network in the ventral temporal lobe of awake and anesthetized macaques. Neuron 70 (2011), 352–362.
11. 11 Afraz, A., Boyden, E.S., DiCarlo, J.J., Optogenetic and pharmacological suppression of spatial clusters of face neurons reveal their causal role in face gender discrimination. Proc. Natl. Acad. Sci. USA 112 (2015), 6730–6735.
12. 12 Moeller, S., Freiwald, W.A., Tsao, D.Y., Patches with links: a unified system for processing faces in the macaque temporal lobe. Science 320 (2008), 1355–1359.
13. 13 Tsao, D.Y., Moeller, S., Freiwald, W.A., Comparing face patch systems in macaques and humans. Proc. Natl. Acad. Sci. USA 105 (2008), 19514–19519.
14. 14 Riesenhuber, M., Poggio, T., Hierarchical models of object recognition in cortex. Nat. Neurosci. 2 (1999), 1019–1025.
15. 15 Poggio, T., Edelman, S., A network that learns to recognize three-dimensional objects. Nature 343 (1990), 263–266.
16. th European Conference on Computer Vision, Prague, Czech Republic, May 2004 Proceedings, Part II, 2004, Springer, 152–165.
17. 17 Leibo, J.Z., Liao, Q., Anselmi, F., Poggio, T., The invariance hypothesis implies domain-specific regions in visual cortex. PLoS Comput. Biol., 11, 2015, e1004390.
18. 18 Farzmahdi, A., Rajaei, K., Ghodrati, M., Ebrahimpour, R., Khaligh-Razavi, S.M., A specialized face-processing model inspired by the organization of monkey face patches explains several face-specific phenomena observed in humans. Sci. Rep., 6, 2016, 25025.
19. 19 Hung, C.P., Kreiman, G., Poggio, T., DiCarlo, J.J., Fast readout of object identity from macaque inferior temporal cortex. Science 310 (2005), 863–866.
20. 20 Meyers, E.M., Borzello, M., Freiwald, W.A., Tsao, D., Intelligent information loss: the coding of facial identity, head pose, and non-face information in the macaque face patch system. J. Neurosci. 35 (2015), 7069–7081.
21. 21 Thorpe, S., Fize, D., Marlot, C., Speed of processing in the human visual system. Nature 381 (1996), 520–522.
22. 22 Isik, L., Meyers, E.M., Leibo, J.Z., Poggio, T., The dynamics of invariant object recognition in the human visual system. J. Neurophysiol. 111 (2014), 91–102.
23. 23 Bruce, V., Young, A., Understanding face recognition. Br. J. Psychol. 77 (1986), 305–327.
24. 24 Tan, C., Poggio, T., Neural tuning size in a model of primate visual processing accounts for three key markers of holistic face processing. PLoS ONE, 11, 2016, e0150980.
25. 25 Adelson, E.H., Bergen, J.R., Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A 2 (1985), 284–299.
26. 26 Isik, L., Leibo, J.Z., Poggio, T., Learning and disrupting invariance in visual recognition with a temporal association rule. Front. Comput. Neurosci., 6, 2012, 37.
27. 27 Hinton, G.E., and Becker, S. (1990). An unsupervised learning procedure that discovers surfaces in random-dot stereograms. In Proceedings of the IEEE/INNS International Joint Conference on Neural Networks 1, 218–222.
28. 28 Földiák, P., Learning invariance from transformation sequences. Neural Comput. 3 (1991), 194–200.
29. 29 Wiskott, L., Sejnowski, T.J., Slow feature analysis: unsupervised learning of invariances. Neural Comput. 14 (2002), 715–770.
30. 30 Berkes, P., Turner, R.E., Sahani, M., A structured model of video reproduces primary visual cortical organisation. PLoS Comput. Biol., 5, 2009, e1000495.
31. 31 Miyashita, Y., Neuronal correlate of visual associative long-term memory in the primate temporal cortex. Nature 335 (1988), 817–820.
32. 32 Wallis, G., Bülthoff, H.H., Effects of temporal association on recognition memory. Proc. Natl. Acad. Sci. USA 98 (2001), 4800–4804.
33. 33 Cox, D.D., Meier, P., Oertelt, N., DiCarlo, J.J., ‘Breaking’ position-invariant object recognition. Nat. Neurosci. 8 (2005), 1145–1147.
34. 34 Li, N., DiCarlo, J.J., Unsupervised natural visual experience rapidly reshapes size-invariant object representation in inferior temporal cortex. Neuron 67 (2010), 1062–1075.
35. 35 Anselmi, F., Rosasco, L., and Poggio, T. (2015). On invariance and selectivity in representation learning. arXiv, arXiv:1503.05938, http://arxiv.org/abs/1503.05938.
36. 36 Hassoun, M.H., Fundamentals of Artificial Neural Networks. 1995, MIT Press.
37. 37 Oja, E., A simplified neuron model as a principal component analyzer. J. Math. Biol. 15 (1982), 267–273.
38. 38 Oja, E., Principal components, minor components, and linear neural networks. Neural Netw. 5 (1992), 927–935.
39. 39 Abbott, L.F., Nelson, S.B., Synaptic plasticity: taming the beast. Nat. Neurosci. 3 (2000), 1178–1183.
40. 40 Sanger, T.D., Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Netw. 2 (1989), 459–473.
41. 41 Keck, T., Keller, G.B., Jacobsen, R.I., Eysel, U.T., Bonhoeffer, T., Hübener, M., Synaptic scaling and homeostatic plasticity in the mouse visual cortex in vivo. Neuron 80 (2013), 327–334.
42. 42 Hengen, K.B., Lambo, M.E., Van Hooser, S.D., Katz, D.B., Turrigiano, G.G., Firing rate homeostasis in visual cortex of freely behaving rodents. Neuron 80 (2013), 335–342.
43. 43 Turrigiano, G.G., Nelson, S.B., Homeostatic plasticity in the developing nervous system. Nat. Rev. Neurosci. 5 (2004), 97–107.
44. 44 Yildirim, I., Kulkarni, T.D., Freiwald, W.A., and Tenenbaum, J.B. (2015). Efficient and robust analysis-by-synthesis in vision: a computational framework, behavioral tests, and modeling neuronal representations. In Proceedings of the Annual Conference of the Cognitive Science Society.