I just began my Deep learning journey with Keras along with Tenserflow. I followed a tutorial that used a feed forward model on MNIST dataset. The strange part is that I used the same complied code, yet, I got a higher accuracy rate than the exact same code. I'm looking to understand why or how can this happen?
Asked
Active
Viewed 22 times
0
-
Are both scripts using the same random seed? – KonstantinosKokos Jan 23 '19 at 08:08
-
Possible duplicate of [Neural network gives different results for each execution](https://stackoverflow.com/questions/45953242/neural-network-gives-different-results-for-each-execution) – dennlinger Jan 23 '19 at 09:29
-
This is the exact code I used, found in this link: (scroll all the way to the end of the post for the full code) https://pythonprogramming.net/introduction-deep-learning-python-tensorflow-keras/ – Mya Mariam Jan 27 '19 at 18:32
-
Thanks for the hint. I think I found my answer. It turns out this a common misunderstanding for beginners. I will need to further experiment to thoroughly understand how this works. https://machinelearningmastery.com/tutorial-first-neural-network-python-keras/ – Mya Mariam Jan 27 '19 at 18:59