Abstract | ||
---|---|---|
As a model of a machine learning, an incompletely specified classification function is used. As a benchmark problem, data for handwritten digits with 28 × 28 images were used. This data was converted into one with 14×14 = 196 pixels using a space filter. Also, the value of each pixel was binarized. With this operation, the original data was converted into a 196variable classification function that takes values from 0 to 9. For the training data, we had k = 58191 samples. Using a linear transformation, the 196-variable classification function was converted into a 25-variable function. We applied the testing data consisting of 9569 samples. The reduced classification function produced correct answers for 97.3% of the recognized test data. For unrecognized test data, the circuit for the reduced classification function produced "unrecognized" signals. The recognition circuit for handwritten digits can be implemented by a simple architecture: a cascade of a linear circuit and a memory. To increase the recognition rate, we also present methods using multiple classification functions and voters. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ISMVL49045.2020.00-18 | 2020 IEEE 50th International Symposium on Multiple-Valued Logic (ISMVL) |
Keywords | DocType | ISSN |
linear decomposition,partially defined function,support minimization,classification,digit recognition,Occam’s razor,index generation function,machine learning | Conference | 0195-623X |
ISBN | Citations | PageRank |
978-1-7281-5407-7 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tsutomu Sasao | 1 | 1083 | 141.62 |
Yuto Horikawa | 2 | 0 | 0.34 |
yukihiro iguchi | 3 | 85 | 13.24 |