Based on the incremental nature of knowledge acquisition, in this study we propose a growing self-organizing neural network approach for modeling the acquisition of auditory and semantic categories. We introduce an Interconnected Growing Self-Organizing Maps (I-GSOM) algorithm, which takes associations between auditory information and semantic information into consideration, in this paper. Direct phonetic–semantic association is simulated in order to model the language acquisition in early phases, such as the babbling and imitation stages, in which no phonological representations exist. Based on the I-GSOM algorithm, we conducted experiments using paired acoustic and semantic training data. We use a cyclical reinforcing and reviewing training procedure to model the teaching and learning process between children and their communication partners. A reinforcing-by-link training procedure and a link-forgetting procedure are introduced to model the acquisition of associative relations between auditory and semantic information. Experimental results indicate that (1) I-GSOM has good ability to learn auditory and semantic categories presented within the training data; (2) clear auditory and semantic boundaries can be found in the network representation; (3) cyclical reinforcing and reviewing training leads to a detailed categorization as well as to a detailed clustering, while keeping the clusters that have already been learned and the network structure that has already been developed stable; and (4) reinforcing-by-link training leads to well-perceived auditory–semantic associations. Our I-GSOM model suggests that it is important to associate auditory information with semantic information during language acquisition. Despite its high level of abstraction, our I-GSOM approach can be interpreted as a biologically-inspired neurocomputational model.

Muscle activations during speech production are important for understanding speech motor control. In this paper, we put forward a physiological articulatory model-based approach to estimate muscle activations in producing five sustained Japanese vowels by minimizing the morphological difference between model simulations and target MRI observations, where the model is an improved version of Dang's partial 3D model. The initial muscle activations in the model simulation are set according to observation obtained by EMG measurement in producing vowels [6]. Then, the activation level of the tongue muscles are gradually adjusted so as to reduce the difference between the simulations and target MRI observations using an optimization approach. The results show that the proposed method can provide more details of the muscle activations than that obtained by EMG. In addition, the results suggest that the muscles Transversus and Verticalis play important roles in manipulating the length of tongue for vowel production; and, it is better to separate the Styloglossus into two control units, the anterior portion and posterior portion, in vowel production.

Deep reinforcement learning has achieved some remarkable results in self-driving. There is quite a lot of work to do in the area of autonomous driving with high real-time requirements because of the inefficiency of reinforcement learning in exploring large continuous motion spaces. A deep imitation reinforcement learning (DIRL) framework is presented to learn control policies of self-driving vehicles, which is based on a deep deterministic policy gradient algorithm (DDPG) by vision. The DIRL framework comprises two components, the perception module and the control module, using imitation learning (IL) and DDPG, respectively. The perception module employs the IL network as an encoder which processes an image into a low-dimensional feature vector. This vector is then delivered to the control module which outputs control commands. Meanwhile, the actor network of the DDPG is initialized with the trained IL network to improve exploration efficiency. In addition, a reward function for reinforcement learning is defined to improve the stability of self-driving vehicles, especially on curves. DIRL is verified by the open racing car simulator (TORCS), and the results show that the correct control strategy is learned successfully and has less training time.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

No abstract