| 1. | Another training rule is the delta rule
另一种培训的规则叫做delta规则。 |
| 2. | The delta rule is defined in terms of this definition of error
Delta规则就是依据这个误差的定义来定义的。 |
| 3. | A delta rule - based algorithm for weight modification looks like this
用于权系数调节的基于delta规则的算法就是如此。 |
| 4. | For some of the minutiae of the delta rule , see kevin gurney s excellent
关于一些delta规则的详细信息，请参阅kevin gurney的著作 |
| 5. | The delta rule
关于delta规则 |
| 6. | However , the delta rule rests on refinements in the notions of average and error
但是delta规则取决于求平均值方法的精确度以及误差。 |
| 7. | The practice algorithm is similar to delta rule . with long period developing , bpn has been improved
其学习算法是学习算法的推广和发展，是一种有导师的学习。 |
| 8. | Is an algorithm that extends the analysis that underpins the delta rule to neural nets with hidden nodes
这一算法把支持delta规则的分析扩展到了带有隐藏节点的神经网络。 |
| 9. | The delta rule algorithm always makes a change in weights , and it is based on activation as opposed to output
Delta规则算法总是在权系数上调整，而且这是建立在相对输出的激活方式上。 |
| 10. | Because error is explained in terms of all the training vectors , the delta rule is an algorithm for taking a particular set of weights and a particular vector , and yielding weight changes that would take the neural net on the path to minimal error
因为误差是依据那些培训向量来说明的， delta规则是一种获取一个特殊的权系数集以及一个特殊的向量的算法。而改变权系数将会使神经网络的误差最小化。 |
