This chapter discusses a two-layer competitive learning network for unsupervised clustering based on a competitive learning rule. The weights of each node of the output layer are treated as a vector, in the same space for the input vectors. Given an input, all nodes compete to become the sole winner (winner-take-all) with the highest output value, so that its weights can be modified in such a way that it will be more likely to win when the same input is presented to the input layer next time. By the end of this iterative learning process, each weight vector is gradually moved toward the center of one of the clusters in the space, thereby representing the cluster. The chapter further considers the self organizing map (SOM), a network based on the same competitive learning rule, but modified in such a way that nodes in the neighborhood of the winner learn along with the winner by modifying their weights as well but to a lesser extent. Once fully trained, the SOM achieves the effect that neighboring nodes learn to respond to similar inputs, mimicking a typical behavior of certain visual and auditory cortex in the brain.

Feedback in its actual forms has gained momentum because many developments in teaching and learning in schools and in the foreign-language classroom in particular have facililtated the implementation of a feedback culture. In the last decades, education in schools has become more and more learner-oriented. On this basis, formative feedback practices have become more and more important and specified in order to help teachers and learners to overcome the concentration on the person of the teacher and on drill-based forms of instruction. Today, feedback is no longer a one-way road, but also reaches teachers and is complemented by various other forms of feedback. This general positive development was further promoted by the changes in foreign-language instruction from the Grammar-Translation-Method to Intercultural Communication, with the aim of coming as close to real-life settings as possible.