Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
leiyycoco
d2a6cea177
|
1 year ago | |
|---|---|---|
| SaveModel | 1 year ago | |
| README.md | 1 year ago | |
| data.py | 1 year ago | |
| feature.py | 1 year ago | |
| main.py | 1 year ago | |
| 需求预测模型.pdf | 1 year ago | |
README.md
Demand Forecasting
Author: Yuanyuan Lei, Fengming Cui
This is a implenmentaion for combining Neural Network and Hidden Markov Model to conduct demand forecasting.
Key Arguments
Some key arguments:
hidden_dim: the dimension of hidden layer
learning_rate: the learning rate of gradient descent
reg: the regulation intensity
momentum_value: the momentum value in the optimization method
Epochs: the num of iterative traing cycles
num_classes_sa: the num of unknown parameters in the state action matrix
num_classes_s: the num of unknown parameters in the state matrix
Pi_0: the parameter of initial state probability
Model
The trained model is saved in the file "SaveModel".
This is an implenmentaion for combining Neural Network and Hidden Markov Model to conduct demand forecasting.
Python Pickle