It's a simple application of neural network.After several times of training on sample data,it can make a prediction about your taste. Here is the live demo, you'd better access it using mobile phone.
- The training process can be understood as persistently calibrating all of the “weights” by repeating two key steps, forward propagation and back propagation.
- In forward propagation, it receives some input data and apply a set of weights to it and then calculate an output.
- In back propagation, it measure the margin of error of the output and adjust the weights accordingly to decrease the error.
- Using sigmoid function as the activation function to transform the input signal into an output signal.
MIT