发明名称 |
Method of training a neural network |
摘要 |
A state vector (SVt) is determined with elements that characterize a financial market (101). Taking into account predetermined evaluation variables, an evaluation (Vt) is determined (102) for the state vector (SVt). In addition, a chronologically following state vector (SVt+1) is determined (103) and evaluated (Vt+1). On the basis of the two evaluations (Vt, Vt+1), weights (wi) of the neural network (NN) are adapted (104) using a reinforcement learning method (DELTAwi).
|
申请公布号 |
US6247001(B1) |
申请公布日期 |
2001.06.12 |
申请号 |
US19980142275 |
申请日期 |
1998.09.03 |
申请人 |
SIEMENS AKTIENGESELLSCHAFT |
发明人 |
TRESP VOLKER;NEUNEIER RALPH |
分类号 |
G06F15/18;G06N3/00;G06N3/08;G06Q40/00;G06Q90/00;(IPC1-7):G06F9/445 |
主分类号 |
G06F15/18 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|