--Incremental MNIST: Incremental MNIST dataset,including a training file and 4 testing files, which named as ldx_t.mat, lux_t.mat, rdx_t.mat and rux_t.mat.
--Draw.py: Draw the accuracy performance curve.
--Dataset.py: Prepare Incremental MNIST dataset.
--Test.py: Test performance of some model.
--IADM.py: A demo of our method.

--alp : Percentage of Fisher Information accumulated during Backpropagation.
--lr : Learning rate of our model
--drawstep: The frequence of Test duiring training (number of instance,default:12000)
--lamda : The regularization parameter in our paper.(In Eq(5).)

python IADM.py 

@inproceedings{yang2019adaptive,
author = {Yang, Yang and Zhou, Da-Wei and Zhan, De-Chuan and Xiong, Hui and Jiang, Yuan},
title = {Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability},
booktitle = {KDD},
address = {Anchorage, AK},
pages = {74--82},
year = {2019}
}