Recurrent neural networks have recently been demonstrated to have the ability to learn simple grammars. In particular, networks using second-order units have been successfully at this task. However, it is often difficult to predict the optimal neural network size to induce an unknown automaton from examples. Instead of just adjusting the weights in a… (More)
With the maturity of network technology, autonomous learning has become a heated issue. In this paper, an analysis of five elements that affect web-based autonomous learning is presented and an autonomous learning mode is put forward, in the hope of exploring a more effective way of improving learners' English learning autonomy.