Question

帮忙翻译一下自动化专业英语，万分感谢！！急用！

The paradigm has been tested using systematic benchmark tests as well as observing its performance on applications that are known to be difficult. The neural-net application described in Section 3.4, for instance, showed that the particle swarm optimizer could train NN weights as effectively as the usual error backpropagation method. The particle swarm optimizer has also been used to train a neural network to classify the Fisher Iris Data Set [3]. Again, the optimizer trained the weights as effectively as the backpropagation method. Over a series of ten training sessions, the particle swarm optimizer paradigm required an average of 284 epochs. Intriguing informal indications are that the trained weights found by particle swarms sometimes generalize from a training set to a test set better than solutions found by gradient descent. For example, on a data set representing electroencephalogram spike waveforms and false positives, a backpropagation NN achieved 89 percent correct on the test data [2]. The particle swarm optimizer was able to train the network so as to achieve 92 percent correct. The particle swarm optimizer was compared to a benchmark for genetic algorithms in Davis [1]: the extremely nonlinear Schaffer f6 function. This function is very difficult to optimize, as the highly discontinuous data surface features many local optima. The particle swarm paradigm found the global optimum each run, and appears to approximate the results reported for elementary genetic algorithms in Chapter 2 of [1] in terms of the number of evaluations required to reach certain performance levels.

Answer 1

什么都不说 晕了