A Probabilistic View of the Spatial Pooler in Hierarchical Temporal Memory
In the Hierarchical Temporal Memory (HTM) paradigm
the effect of overlap between inputs on the activation of columns in
the spatial pooler is studied. Numerical results suggest that similar
inputs are represented by similar sets of columns and dissimilar inputs
are represented by dissimilar sets of columns. It is shown that the
spatial pooler produces these results under certain conditions for
the connectivity and proximal thresholds. Following the discussion
of the initialization of parameters for the thresholds, corresponding
qualitative arguments about the learning dynamics of the spatial
pooler are discussed.
[1] B. Bobier and M.Wirth, “Content-based image retrieval using hierarchical
temporal memory,” in Proc. 16th ACM Int. Conf. on Multimedia, 2008,
pp. 925-928.
[2] P. Gabrielsson, R. Konig, and U. Johansson, “Evolving hierarchical
temporal memory-based trading models,” in EvoApplications
2013-Applications of Evolutionary Computing, Vienna, April 3-5,
2013.
[3] J. Hawkins, S. Ahmad, and D. Dubinsky, “Hierarchical temporal memory
including HTM cortical learning algorithms,” Numenta, Redwood City,
CA, Tech. Rep. ver. 0.2.1, 2011.
[4] D.O. Hebb, ”The first stage of perception: growth of the assembly,” in
The Organization of Behavior, New York, Wiley, 1949, intro. and ch. 4,
pp. xi-xix, 60-78.
[5] D. Maltoni, “Pattern recognition by hierarchical temporal memory,” DEIS
Univ. Bologna, Tech. Rep., pp. 1-46, Apr. 13, 2011.
[6] V. Mountcastle, “The columnar organization of the neocortex,” Brain, vol.
120(4), pp. 701-722, 1997.
[7] A.J. Perea, J.E. Merono, and M.J. Aguilera, “Application of Numenta
hierarchical temporal memory for land-use classification,” S. Afr. J. Sci.,
vol. 105, pp. 370-375, Sept./Oct. 2009.
[8] J. Thornton and A. Srbic, “Spatial pooling for greyscale images,” Int. J.
Mach. Learn. & Cyber., vol. 4, pp. 207-216, 2013.
[9] J. van Doremalen and L. Boves, “Spoken digit recognition using a
hierarchical temporal memory,” Interspeech, pp. 2566-2569, Brisbane,
Sept. 22-26, 2008.
[1] B. Bobier and M.Wirth, “Content-based image retrieval using hierarchical
temporal memory,” in Proc. 16th ACM Int. Conf. on Multimedia, 2008,
pp. 925-928.
[2] P. Gabrielsson, R. Konig, and U. Johansson, “Evolving hierarchical
temporal memory-based trading models,” in EvoApplications
2013-Applications of Evolutionary Computing, Vienna, April 3-5,
2013.
[3] J. Hawkins, S. Ahmad, and D. Dubinsky, “Hierarchical temporal memory
including HTM cortical learning algorithms,” Numenta, Redwood City,
CA, Tech. Rep. ver. 0.2.1, 2011.
[4] D.O. Hebb, ”The first stage of perception: growth of the assembly,” in
The Organization of Behavior, New York, Wiley, 1949, intro. and ch. 4,
pp. xi-xix, 60-78.
[5] D. Maltoni, “Pattern recognition by hierarchical temporal memory,” DEIS
Univ. Bologna, Tech. Rep., pp. 1-46, Apr. 13, 2011.
[6] V. Mountcastle, “The columnar organization of the neocortex,” Brain, vol.
120(4), pp. 701-722, 1997.
[7] A.J. Perea, J.E. Merono, and M.J. Aguilera, “Application of Numenta
hierarchical temporal memory for land-use classification,” S. Afr. J. Sci.,
vol. 105, pp. 370-375, Sept./Oct. 2009.
[8] J. Thornton and A. Srbic, “Spatial pooling for greyscale images,” Int. J.
Mach. Learn. & Cyber., vol. 4, pp. 207-216, 2013.
[9] J. van Doremalen and L. Boves, “Spoken digit recognition using a
hierarchical temporal memory,” Interspeech, pp. 2566-2569, Brisbane,
Sept. 22-26, 2008.
@article{"International Journal of Information, Control and Computer Sciences:69983", author = "Mackenzie Leake and Liyu Xia and Kamil Rocki and Wayne Imaino", title = "A Probabilistic View of the Spatial Pooler in Hierarchical Temporal Memory", abstract = "In the Hierarchical Temporal Memory (HTM) paradigm
the effect of overlap between inputs on the activation of columns in
the spatial pooler is studied. Numerical results suggest that similar
inputs are represented by similar sets of columns and dissimilar inputs
are represented by dissimilar sets of columns. It is shown that the
spatial pooler produces these results under certain conditions for
the connectivity and proximal thresholds. Following the discussion
of the initialization of parameters for the thresholds, corresponding
qualitative arguments about the learning dynamics of the spatial
pooler are discussed.", keywords = "Hierarchical Temporal Memory, HTM, Learning
Algorithms, Machine Learning, Spatial Pooler.", volume = "9", number = "5", pages = "1275-8", }