Please Note

The paper ``Evolutionary Techniques for Fault Tolerance'' and its journal version ``Evolving Inherently Fault-Tolerant Systems'' contain a small technical error. The text defines a measure

$$\hat{e} = \left( \overline{e} \left/ \mbox{ } \overline{\mbox{evolved fitness}} \right.\right) \times 100\% \nonumber$$

whereas the correct definition is

$$\hat{e} = \left( \overline{e} \left/ \mbox{ }\overline{f_{d}^*} \right.\right) \times 100\% \nonumber$$

The graphs, and all of the discussion and conclusions, are unaffected; only the original definition of $\hat{e}$ in the text is in error.

Adrian Thompson, 1998.