DeepCF: A Deep Feature Learning-Based Car-Following Model Using Online Ride-Hailing Trajectory Data

Algorithm 1. Minibatch stochastic gradient descent training algorithm for generating adversarial networks.

Input:

Training set data distribution ; random noise distribution ; Total training times epochs; the number of iterations of the discriminator k; the learning rate of the discriminator ; the learning rate of the generator ; the amount of training data per batch n.

Output:

The network parameters of the discriminator ; network parameters of the generator .

Begin

1. Initialize ,

2. For epochs do

3. For k do

4. Sample n samples from the random noise distribution

5. Sample n samples from the real data distribution

6. Update by boosting the stochastic gradient:

7. 

8. End for

9. Sample n samples from the random noise distribution

10. Update with gradient by decreasing:

11.

12.

Algorithm 1. Minibatch stochastic gradient descent training algorithm for generating adversarial networks.