The following environments are required:
- Python 3.7 (anaconda is preferable)
- tensorflow 2.0
You can install the package by the following console command:
pip install git+https://github.com/zebinyang/exnn.gitIf git is not available, you can manually install the package by downloading the source codes and then compiling it by hand:
-
Download the source codes from https://github.com/ZebinYang/exnn.git.
-
unzip and switch to the root folder.
-
Run the following shell commands to finish installation.
pip install -r requirements.txt
python setup.py installimport numpy as np
import tensorflow as tf
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
from exnn import ExNN
def data_generator1(datanum, testnum=10000, noise_sigma=1, rand_seed=0):
corr = 0.5
np.random.seed(rand_seed)
proj_matrix = np.zeros((10, 4))
proj_matrix[:7, 0] = np.array([1,0,0,0,0,0,0])
proj_matrix[:7, 1] = np.array([0,1,0,0,0,0,0])
proj_matrix[:7, 2] = np.array([0,0,0.5,0.5,0,0,0])
proj_matrix[:7, 3] = np.array([0,0,0,0,0.2,0.3,0.5])
u = np.random.uniform(-1, 1, [datanum + testnum, 1])
t = np.sqrt(corr / (1 - corr))
x = np.zeros((datanum + testnum, 10))
for i in range(10):
x[:, i:i + 1] = (np.random.uniform(-1, 1, [datanum + testnum, 1]) + t * u) / (1 + t)
y = np.reshape(2 * np.dot(x, proj_matrix[:, 0]) + 0.2 * np.exp(-4 * np.dot(x, proj_matrix[:, 1])) + \
3 * (np.dot(x, proj_matrix[:, 2]))**2 + 2.5 * np.sin(np.pi * np.dot(x, proj_matrix[:, 3])), [-1, 1]) + \
noise_sigma * np.random.normal(0, 1, [datanum + testnum, 1])
task_type = "Regression"
meta_info = {"X1":{"type":"continuous"},
"X2":{"type":"continuous"},
"X3":{"type":"continuous"},
"X4":{"type":"continuous"},
"X5":{"type":"continuous"},
"X6":{"type":"continuous"},
"X7":{"type":"continuous"},
"X8":{"type":"continuous"},
"X9":{"type":"continuous"},
"X10":{"type":"continuous"},
"Y":{"type":"target"}}
for i, (key, item) in enumerate(meta_info.items()):
if item['type'] == "target":
sy = MinMaxScaler((-1, 1))
y = sy.fit_transform(y)
meta_info[key]["scaler"] = sy
elif item['type'] == "categorical":
enc = OrdinalEncoder()
enc.fit(x[:,[i]])
ordinal_feature = enc.transform(x[:,[i]])
x[:,[i]] = ordinal_feature
meta_info[key]["values"] = enc.categories_[0].tolist()
else:
sx = MinMaxScaler((-1, 1))
x[:,[i]] = sx.fit_transform(x[:,[i]])
meta_info[key]["scaler"] = sx
train_x, test_x, train_y, test_y = train_test_split(x, y, test_size=testnum, random_state=rand_seed)
return train_x, test_x, train_y, test_y, task_type, meta_info
train_x, test_x, train_y, test_y, task_type, meta_info = data_generator1(datanum=10000, testnum=10000, noise_sigma=1, rand_seed=0)
model = ExNN(meta_info=meta_info,
subnet_num=10,
subnet_arch=[10, 6],
task_type=task_type,
activation_func=tf.tanh,
batch_size=min(1000, int(train_x.shape[0] * 0.2)),
training_epochs=10000,
lr_bp=0.001,
lr_cl=0.1,
beta_threshold=0.05,
tuning_epochs=100,
l1_proj=0.0001,
l1_subnet=0.00316,
l2_smooth=10**(-6),
verbose=True,
val_ratio=0.2,
early_stop_thres=500)
model.fit(train_x, train_y)
model.visualize("./", "exnn_demo")@article{yang2021enhancing,
author={Yang, Zebin and Zhang, Aijun and Sudjianto, Agus},
journal={IEEE Transactions on Neural Networks and Learning Systems},
title={Enhancing Explainability of Neural Networks Through Architecture Constraints},
year={2021},
volume={32},
number={6},
pages={2610-2621},
doi={10.1109/TNNLS.2020.3007259}
}