Description: The package includes the MATLAB code of the PUFE (Prediction with Feature Evolvable Streams) which focuses on the learning with feature evolvable streams where the feature's vanishing is not predictable. To run our code, please open the folder called "Code" and use Matlab (Matlab 2018b is preferable) to run demo.m. The accuracy result of each synthetic dataset will be printed. And a folder called "Picture" will appear in which there are figures in pdf. Each figure is the trend of average cumulative loss. "P-dataname" means the overlapping of "dataname" is predictable.
References:
[1] Bo-Jian Hou, Lijun Zhang, and Zhi-Hua Zhou. Prediction with Unpredictable Feature Evolution. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021, in press.
Requirement: The package was developed with MATLAB(R2018b).
ATTN: This package is free for academic usage. You can run it at your own risk. For other purposes, please contact
Prof. Zhi-Hua Zhou.
ATTN2: This package was developed by
Dr. Bo-Jian Hou. For any problem concerning the code, please feel free to contact Dr. Hou.
Download:
code (17.2MB)