**Relevant content viewed in the document**: 

 

 ## References

-----------------------------------

**Relevant content viewed in the document**: 

 

 from:

**N.J., Smelter, & P.B., Baltes (Eds.) (2001).**

**Encyclopedia of the Social and Behavioral Sciences.**

**London: Elsevier Science.**

**Article Title: Linear Algebra for Neural Networks**

**By: Herve Abdi**

**Author Address:** Herve Abdi, School of Human Development, MS: Gr.4.1, The University of Texas at Dallas, Richardson, TX 750833-0688, USA

**Phone:** 972 883 2065, **fax:** 972 883 2491 **Date:** June 1, 2001

**E-mail:** herve@utdallas.edu

**Abstract**

-----------------------------------

**Relevant content viewed in the document**: 

 

 $$o=f\left(a\right)\enspace. \tag{6}$$

For example, in _backpropagation networks_, the (nonlinear) transfer function is usually the logistic function

$$o=f\left(a\right)=\operatorname{logist}\boldsymbol{w}^{\mskip-1.5mu \mathsf{T}} \boldsymbol{x}=\frac{1}{1+\exp\{-a\}}\enspace. \tag{7}$$

-----------------------------------

**Relevant content viewed in the document**: 

 

 $\boldsymbol{x}$, and $\boldsymbol{w}$, the activation of the output cell is obtained as

-----------------------------------