Foreign exchange prediction and trading using deep belief neural network
This project would provide an analysis on the deep belief network (DBN). A DBN would be constructed by stacking layers of restricted Boltzmann machines (RBM), and its learning process will be optimized by various optimization methods. Differing number of inputs, hidden layer and its number of neuron...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/76355 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | This project would provide an analysis on the deep belief network (DBN). A DBN would be constructed by stacking layers of restricted Boltzmann machines (RBM), and its learning process will be optimized by various optimization methods. Differing number of inputs, hidden layer and its number of neurons would also be implemented. A single exchange rate would be tested against a time period while three criteria would be considered to determine its performance. All this would be achieved by using a programming software called MATLAB. |
|---|