diff --git a/README.md b/README.md
index fa9cd1a13edc8e98e44aed17b06cefdffaea5e3c..951a48ba0da72401adc2dfb7223bec360ff29d36 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,22 @@ Task Conditional Neural Networks (TCNN) leverage the probabilistic neural networ
 Then produce the task likelihood during the test state to fire the task-specific neurons correspondin to the test sampels. TCNN can detect and 
 learn the new tasks fully-automatically without informing the changes to the model.
 
-
+The schematic diagram of TCNN learning process.
 ![TCNN_Process](/images/TCNN.png)
 
+
+
+## Dependencies
+
+The code is tested on 
+*  Python 3.6.8
+*  Tensorflow '1.13.1'
+*  Keras '2.2.4'
+
+## Reproduce
+To run the experiment, run the '''split_mnist.py''' files via:
+'''python split_mnist.py'''
+
+The result should be similar to the figure below:
+
+![TCNN_Process](/images/result.png)
\ No newline at end of file