Artificial Intelligence (AI) and Machine learning education are entering the classrooms, and yet, the link between their introduction and the development of metacognitive components in students still needs to be addre...
详细信息
ISBN:
(纸本)9783031384530;9783031384547
Artificial Intelligence (AI) and Machine learning education are entering the classrooms, and yet, the link between their introduction and the development of metacognitive components in students still needs to be addressed. We conducted an experiment with 138 elementary school students (aged 8-11) and tested how the manipulation of a learning robot affected their understanding of the basics of AI, as well as their metacognitive knowledge such as growth mindset, status of error, learning by trial-and-error, and persistence. Results show a positive shift both in students' AI knowledge and learning beliefs, and thus demonstrate the value of teaching the basics of how AI works to develop solid metacognitive knowledge that promotes learning. Future works should measure a lasting effect on students' learning behavior and focus on teacher training in new AI activities.
To study the autonomous learning model of the learning robot for marine resource exploration, an adaptive neural network controller was applied. The motion characteristics of autonomous learning robots were identified...
详细信息
To study the autonomous learning model of the learning robot for marine resource exploration, an adaptive neural network controller was applied. The motion characteristics of autonomous learning robots were identified. The mathematical model of the multilayer forward neural network and its improved learning algorithm were studied. The improved Elman regression neural network and the composite input dynamic regression neural network were further discussed. At the same time, the diagonal neural network was analysed from the structure and learning algorithms. The results showed that for the complex environment of the ocean, the structure of the composite input dynamic regression network was simple, and the convergence was fast. In summary, the identification method of underwater robot system based on neural network is effective.
Building robots is generally considered difficult, because the designer not only has to predict the interactions between the robot and the environment, but also has to deal with the consequent problems. In recent year...
详细信息
Building robots is generally considered difficult, because the designer not only has to predict the interactions between the robot and the environment, but also has to deal with the consequent problems. In recent years, evolutionary algorithms have been proposed to synthesize robot controllers. However, admittedly, it is not satisfactory enough just to evolve the control system, because the performance of the control system depends on other hardware parameters - the robot body plan - which might include body size, wheel radius, motor time constant, etc. Therefore, the robot body plan itself should, ideally, also adapt to the task that the evolved robot is expected to accomplish. In this paper, a hybrid GP/GA framework is presented to evolve complete robot systems, including controllers and bodies, to achieve fitness-specified tasks. In order to assess the performance of the developed system, we use it with a fixed robot body plan to evolve controllers for a variety of tasks at first, then to evolve complete robot systems. Experimental results show the promise of our system.
暂无评论