Search

In this article, we investigate the relative performance of artificial neural networks and structural models of decision theory by training 69 artificial intelligence models on a dataset of 7080 human decisions in extensive form games. The objective is to compare the predictive power of AIs that use a representation of another agent's decision-making process in order to improve their own performance during a strategic interaction. We use human game theory data for training and testing. Our findings hold implications for understanding how AIs can use constrained structural representations of other decision makers, a crucial aspect of our 'Theory of Mind'. We show that key psychological features, such as the Weber–Fechner law for economics, are evident in our tests, that simple linear models are highly robust, and that being able to switch between different representations of another agent is a very effective strategy. Testing different models of AI-ToM paves the way for the development of learnable abstractions for reasoning about the mental states of 'self' and 'other', thereby providing further insights for fields such as social robotics, virtual assistants, and autonomous vehicles, and fostering more natural interactions between people and machines. [ABSTRACT FROM AUTHOR]

Modern e-learning system is a representative service form in innovative service industry. This paper designs a personalized service domain system, optimizes various parameters and can be applied to different education quality evaluation, and proposes a decision tree recommendation algorithm. Information gain is carried out through many existing principles of improved decision tree algorithm, and the information gain of the algorithm determines the inheritance of information. The process of modern e-learning system is based on personalized teaching and humanized intelligent interaction. This paper theoretically analyzes the improvement performance of the existing e-learning system in teaching quality evaluation and shows a good classification effect. This model provides reference materials for the expansion of education and teaching and provides a feasible practical model for personalized teaching in online schools. The authors provide good educational conditions and environment for students and cultivate all-around talents for the society. [ABSTRACT FROM AUTHOR]

In this study it is proposed the critical analysis of the creation of Artificial Intelligence (AI) and of Artificial General Intelligence (AGI). The unity of formal logic and rational dialectics is the methodological basis of the analysis. The main results of the analysis are as follows: (1) the model of man represents the unity of the two material aspects: "physiological body" (controllable aspect) and "psychical body" (controlling aspect); (2) the "psychical body" is the subsystem "subconsciousness + consciousness"; (3) in the comprehensive sense of the word, the thinking is an attribute of the complete system "physiological body + psychical body + environment". (3) in the broad sense of the word, thinking and creativity are an essential feature of the subsystem "subconsciousness + consciousness"; (4) in the narrow (concise) sense of the word, thinking and creativity are the attribute of the instinct of the conservation (preservation, retention, maintenance) of life (i.e., the self-preservation instinct, the survival instinct); the instinct of the conservation of life exists in subconsciousness; (5) the instinct of life conservation is a system of elementary (basic) instincts; thinking is the attribute of the each elementary instinct; (6) the mechanism of thinking and the essence of creation cannot be cognized by men; (7) a computer as a device cannot think and create (in particular, it cannot prove theorems), because a computer does not have the subconsciousness; (8) the modeling of human thinking, Human Intellect, and the creation of AI and AGI are the impossible because the essential properties of the complete system "man + environment" cannot be cognized and modeled; (9) the existence of AI and AGI conflicts with the essence of the thinking; (10) the existence of AI and AGI contradict to formal-logical and rationaldialectical laws. [ABSTRACT FROM AUTHOR]

Emotion plays an essential role in the adaptation and social communication of organisms. Similarly, an appropriately timed and clearly expressed emotion is a central requirement for believable interactive virtual humans. Presently, incorporating emotion into virtual humans has gained increasing attention in the academia and industry. This strong interest is driven by a wide spectrum of promising applications in many areas such as virtual reality, e-learning, entertainment, etc. This paper introduces an emotion model of artificial psychology, in which the transition of emotion can be viewed as a Markov process and the relation of emotion, external incentive and personality can be described by a Markov decision process (MDP). In order to demonstrate the approach, this paper integrates the emotion model into a system composed of voice recognition and a realistic facial model. Thus, the model could be used for generating a variety of emotional expressions of autonomous, interactive virtual human beings. [ABSTRACT FROM AUTHOR]