Digit Recognition App
The Digit Recognition App shows the use of a convolutional neural network model that it was built and trained with Keras on top of Tensorflow.
I trained the model on the MNIST dataset in order to create an app that can recognize handwritten digits.
The model (based on Keras Example) is integrated in iOS and it can be accessed in code via the CoreML and Vision Api, introduced by Apple at WWDC17. It is also integrated in Android and it is accessible in code via the TensorFlow Lite solution.
Artificial Neural Network
In information technology (IT), a neural network is a system of hardware and/or software patterned after the operation of neurons in the human brain. Neural networks, also called artificial neural networks, are a variety of deep learning technology, which also falls under the umbrella of artificial intelligence, or AI.
How artificial neural networks work
A neural network usually involves a large number of processors operating in parallel and arranged in tiers. The first tier receives the raw input information, analogous to optic nerves in human visual processing. Each successive tier receives the output from the tier preceding it, rather than from the raw input, in the same way neurons further from the optic nerve receive signals from those closer to it. The last tier produces the output of the system.
I’ll release the Apps in the next days but, if you want, you can test the Preview Apps.
Please do not hesitate to contact me for further information about testing.
Apple, the Apple logo, iPhone, and iPad are trademarks of Apple Inc., registered in the U.S. and other countries and regions. App Store is a service mark of Apple Inc.
Google Play and the Google Play logo are trademarks of Google LLC.
This is my first approach to Artificial Intelligence so next steps are to improve the model (actually get to 99% test accuracy but there is still a lot of margin), improve the Apps, and move to the next challenge.
The iOS App is inspired by the work of akhilwaghmare, while the Android App is inspired by the work of OmarAflak.
The Icons are made by Freepik from flaticon.com and is licensed by CC 3.0 BY.
Thanks to Udacity for the inspirational Deep Learning Course.
And last but not least I would like to thank my friends, Andrea Ponti and Edoardo Silva.