Using Deep Learning on MNIST dataset to build Human-Verification website
In this website, we ask the user to enter three random digits, and using Deep Learning on the MNIST dataset we validate the numbers drawn by the user. This is a 3-hidden layer neural network along with input and output layer. All the layers use the ReLU as an activation function except the last layer which is softmax as we need to classify so we want to get probabilities in the last step to determine the highest probability as the predicted digit. I am using Adam Optimizer and for the loss function, I am using the softmax cross-entropy function.
Live Demo - Human Verification Portal
- TensorFlow
- OpenCV
- JavaScript
- Accuracy on Test Dataset is 97.23% .
.
|-- Model
| |-- group1-shard1of1.bin
| `-- model.json
|-- README.md
|-- README_IMAGES
| |-- Confusion_Matrix.png
| |-- Dataset_Splitting.png
| |-- Dataset_analysis.png
| |-- Final-Hyperparameters.png
| |-- NN.png
| |-- Notation.png
| |-- Performance-Accurance.png
| |-- Performance-Cost.png
| |-- Result.png
| |-- Website_Test_Cases.png
| `-- image8.gif
|-- canvas-drawing.js
|-- index.html
|-- opencv.js
|-- predictor.js
`-- validator.js
- LinkedIn - Srinivas K