The biologically inspired Hierarchical Temporal Memory Model for Farsi Handwritten Digit and Letter Recognition

Abstract

It is herein proposed a handwritten digit recognition system which biologically inspired of the large-scale structure of the mammalian neocortex. Hierarchical Temporal Memory (HTM) is a memory-prediction network model that takes advantage of the Bayesian belief propagation and revision techniques. In this article a study has been conducted to train a HTM network to recognize handwritten digits and letters taken from the well-known Hoda dataset for Farsi handwritten digit. Results presented in this paper show good performance and generalization capacity of the proposed network for a real-world big dataset. KeywordsHandwritten digit recognition; hierarchical temporal memory (HTM); Hoda handwritten digits dataset.

A Temporal Pool Learning Algorithm Based on Location Awareness

“…Cell t− 1 from last time (3) For j � 0 to N − 1 do: (4) if j ∈ W t then (5) for i � 0 to M − 1 do ( 6) if π t−1 ij �� 1 then (7) set the current cell to cell t i,j (8) if (learn) then (9) reinforce the segment of the cell; (10) endif ( 11) else (12) select the less used cell to cell t i,j (13) if (learn) (14) create connected segment between cell t i,j and cell t− 1 (15) endif ( 16) endif ( 17) endfor ( 18) else (19) if π t−1 ij �� 1 then (20) if (learn) punish the segment of the cell endif ( 21) endif ( 22) endif ( 23) endfor ( 24) if (learn) A t � Cell t endif (25) Comput the ⊓ t ALGORITHM 1: TPL_LA. Scientific Programming rough F1, it can be seen that TPL_LA is better than TPL.…”

“…Krestinskaya et al develop circuits and systems to achieve the optimized design of an HTM SP, an HTM TM, and a memristive analog pattern matcher for pattern recognition applications [13]. SPL abstracts the input features through a hierarchical structure [14], which makes HTM have wideranging applications in recognition and classification, such as data classification [15], face recognition [16], speech recognition [17], biometric recognition [18], detection of multiple objects located in clutter color images [19], handwriting recognition [20], action recognition [21], gait recognition and understanding [22], and natural language processing [23].…”