Abstract
This chapter presents the way to design a learning support system toward acquiring a creative skill on learning. There are two research goals. One is to establish designing the creative learning task. The other is to make clear the human sense of creativity. As the background of this research, the jobs with high creativity or social skills will remain in the future. However, acquiring human's creativity is too difficult for computers. To solve this problem, the authors focus on the way to utilize higher creativity of human than that of computers. The main method is the visualization of learning traces to support awareness for creativity on the learning. The authors conducted the preliminary learning experiment with three human subjects. After that, the questionnaire and the hearing investigation were conducted. As the future work, the authors are planning to conduct an updated version of the experiment.
TopIntroduction
Recent years in Robotics, there are several researches on biologically inspired approaches (Habib, 2011 & Shi et al., 2015). One of the challenges is to make robots more intelligent learner as a human. This paper describes the learning ability for both human and robot. The missions of this research are to clarify the mechanism of human’s creativity on the learning and to improve the learning abilities both for a human and for intelligent robot. Shi (2015) refers that “Biologically inspired robotics has enabled today’s robots to operate in a variety of unstructured and dynamically changing environments” and “learning often plays an important role in achieving adaption”. To design the learning robots having human-equivalent skill level, there are several targets on human’s intelligent and mental processes such as individual learning, team-based learning or creative thinking (Habib, 2008). This research will contribute the basis of human skill-inspired approach toward designing the creative learning algorithm for intelligent robot to the field of biomimetics.
The progress of information technology will make that about half of human jobs are replaced by computers in near future. The remained jobs having technical difficulty for both AI and computers need high creativity or social skills. According to Boden (2003), “creativity is the ability to come up with ideas or artifacts that are novel and valuable”. Previous research on human creativity suggests that “one process of creating ideas involves making unfamiliar combinations of familiar ideas, requiring a rich store of knowledge” (Frey, C. B., 2015, p.26). However, it is too difficult for robot or computer to acquire human’s creativity. The reason is that creativity is not clear, and the way to learn human’s creativity is not clear. To solve this problem, the authors focus on the interactive way to utilize higher creativity of human than that of robots or computers, and analyze the human’s behaviors with the creativity in the task.
This paper describes how the interactive system inspires the learner to find more learning goals, and this is instrumental in considering the effect of finding of learning goals toward creativity. Research issues of this research are as follows:
- 1.
What is the mechanism of human’s creative learning skill?
- 2.
How is it possible to realize difficult creative learning skill for previous machine learning methods?
- 3.
Why is it important that intelligent systems have human-like creative learning ability?
Our approaches for them are as follows:
- 1.
Designing the creative learning task, then analyzing the human’s learning behaviors to clarify the mechanism of human’s creative learning skill;
- 2.
To make it a goal to realize the human-mimetic learning mechanism;
- 3.
It is important that a learning system is easy to understand the learning property to realize the human friendly intelligent robots or systems.
Key Terms in this Chapter
Deriving a New Achievement from Negating and Shortest Solution: When a learner finds a shortest solution, the system adds a negative sub-reward on one of transitions in the found path to try to negate it.
Redundant Solution: The paths besides shortest solutions and longest solutions.
Learning Goal: A set of solutions in which both the solution quality and the solution size are the same in solutions found at achievements by the learner.
Self-Entropy Based on the Acquired Reward: The difficulty to obtain positive sub-rewards in solutions as the index expressing the solution quality.
Deriving a New Achievement from Justifying a Redundant Solution: When a learner finds a shortest solution, a negative sub-reward is added on one of transitions in the found path to try to negate it.
Shortest Solution: The shortest paths from a start state to an encountering goal state.
Learning Goal Space: The space in which learning goals are positioned to display.