Abstract | ||
---|---|---|
•An online nonlinear regression algorithm is proposed.•Optimal regressor space partition is inferred to manage convergence and undertraining.•Performance of the optimal twice differentiable regression function is achieved.•Performance guarantees hold for any data sequence without any statistical assumptions.•Proposed algorithm is superior over the state-of-the-art techniques. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.patcog.2018.08.014 | Pattern Recognition |
Keywords | Field | DocType |
Online regression,Sequential learning,Nonlinear models,Incremental decision trees | Online algorithm,Decision tree,Nonlinear system,Pattern recognition,Linear model,Algorithm,Nonlinear regression,Artificial intelligence,Piecewise linear function,Statistical assumption,Mathematics,Computational complexity theory | Journal |
Volume | Issue | ISSN |
86 | 1 | 0031-3203 |
Citations | PageRank | References |
1 | 0.35 | 20 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
N. Denizcan Vanli | 1 | 36 | 8.13 |
Muhammed O. Sayin | 2 | 39 | 14.04 |
Mohammadreza Mohaghegh Neyshabouri | 3 | 1 | 1.70 |
Huseyin Ozkan | 4 | 40 | 10.44 |
Suleyman Serdar Kozat | 5 | 121 | 31.32 |