6. [M34] Based on the analyses of Section 5.6.1 complete the prove that OHL nets with single output for linearly-separable examples yield local minima free error functions by proving that the point with all null weights is not a local minimum.

In Section 3.2.2, when discussing linearly-separable examples, it has been proven that for the case logistic sigmoidal units, the condition  = 0 characterizes different stationary points, but the only one which attracts when performing gradient descent is the global minimum. That is, the error surface is local minima free. What happens in the case of the rectifier?