摘要：A generalization by a feedforward neural network is discussed, such that some samples may be generalized using very different, conflicting criteria. A training set is deliberately constructed to show that feedforward neural networks in such a case can generalize very spuriously and randomly. To illustrate the differences between different learning machines, results given by a small subset of the support vector machines are also presented
关键词：supervised learning; generalization; randomness; feedforward neural network; support vector machine
