Abstract | ||
---|---|---|
Inspired by the concept of DNA sequence in biological systems, we developed a novel learning algorithm named DNA-like learning, which is enable to quickly train the CNN template (or named CNN gene) implementing linearly separable Boolean function (LSBF). This algorithm has many advantages including in particular faster running speed and better robustness, and without the need to consider its convergence property. For example, the "AND" and "OR" operations only needs 6 iterations and computations by using the algorithm, compared to the error-correction algorithm which needs 20 operations for the same task, and for judging and implementing a 9-bit linearly separable Boolean function can be finished within only one second on a program based on the new algorithm. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ISCAS.2009.5118359 | ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5 |
Keywords | Field | DocType |
sequences,data mining,cellular neural networks,error correction,convergence,robustness,biological systems,mathematics,probability density function,helium,boolean function,boolean functions,dna sequence,dna | Convergence (routing),Boolean function,Linear separability,Computer science,Algorithm,Error detection and correction,Theoretical computer science,Robustness (computer science),Probability density function,Cellular neural network,Computation | Conference |
Volume | Issue | Citations |
null | null | 1 |
PageRank | References | Authors |
0.36 | 1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fang-yue Chen | 1 | 80 | 18.67 |
Guanrong Chen | 2 | 12378 | 1130.81 |
Qinbin He | 3 | 23 | 3.46 |