Data Mining: Practical Machine Learning Tools and Techniques, Second Edition

228 CHAPTER 6| IMPLEMENTATIONS: REAL MACHINE LEARNING SCHEMES

where f(x) is the network’s prediction obtained from the output unit and yis

the instance’s class label (in this case, it is assumed to be either 0 or 1). The factor

1/2 is included just for convenience, and will drop out when we start taking

derivatives.

Eyfx=-( ( ))

1

2

2

,

0

0.2

0.4

0.6

0.8

1

-10 -5 0 5 10

(a)

0

0.2

0.4

0.6

0.8

1

-10 -5 0 5 10

(b)

Figure 6.11Step versus sigmoid: (a) step function and (b) sigmoid function.