No abstract

No abstract

Abstract. We show that a Multiple Timescale Recurrent Neural Network (MTRNN) can acquire the capabilities of recognizing and generating sentences by self-organizing a hierarchical linguistic structure. There have been many studies aimed at finding whether a neural system such as the brain can acquire languages without innate linguistic faculties. These studies have found that some kinds of recurrent neural networks could learn grammar. However, these models could not acquire the capability of deterministically generating various sentences, which is an essential part of language functions. In addition, the existing models require a word set in advance to learn the grammar. Learning languages without previous knowledge about words requires the capability of hierarchical composition such as characters to words and words to sentences, which is the essence of the rich expressiveness of languages. In our experiment, we trained our model to learn language using only a sentence set without any previous knowledge about words or grammar. Our experimental results demonstrated that the model could acquire the capabilities of recognizing and deterministically generating grammatical sentences even if they were not learned. The analysis of neural activations in our model revealed that the MTRNN had self-organized the linguistic structure hierarchically by taking advantage of differences in the time scale among its neurons, more concretely, neurons that change the fastest represented "characters," those that change more slowly represented "words," and those that change the slowest represented "sentences."

We propose a model of evolutionary communication with voice signs and motion signs between two robots. In our model, a robot recognizes other's action through reflecting its self body dynamics by a Multiple Timescale Recurrent Neural Network (MTRNN). Then the robot interprets the action as a sign by its own hierarchical Neural Network (NN). Each of them modifies their interpretation of signs by re-training the NN to adapt the other's interpretation throughout interaction between them. As a result of the experiment, we found that the communication kept evolving through repeating miscommunication and re-adaptation alternately, and induced the emergence of diverse new signs that depend on the robots' body dynamics through the generalization capability of MTRNN.