Recent interest in human-level intelligence suggests a rethink of the role of machine learning in computational intelligence. We argue that without cognitive learning the goal of achieving human-level synthetic intelligence is far from completion. Here we review the principles underlying human learning and memory, and identify three of them, i.e., continuity, glocality, and compositionality, as the most fundamental to human-level machine learning. We then propose the recently-developed hypernetwork model as a candidate architecture for cognitive learning and memory. Hypernetworks are a random hypergraph structure higher-order probabilistic relations of data by an evolutionary self-organizing process based on molecular selfassembly. The chemically-based massive interaction for information organization and processing in the molecular hypernetworks, referred to as hyperinteractionism, is contrasted with the symbolist, connectionist, and dynamicist approaches to mind and intelligence. We demonstrate the generative learning capability of the hypernetworks to simulate linguistic recall memory, visual imagery, and language-vision crossmodal translation based on a video corpus of movies and dramas in a multimodal memory game environment. We also offer prospects for the hyperinteractionistic molecular mind approach to a unified theory of cognitive learning.

This paper presents a computational theory of developmental mental architectures for artificial and natural systems, motivated by neuroscience. The work is an attempt to approximately model biological mental architectures using mathematical tools. Six types of architecture are presented, beginning with the observation-driven Markov decision process as Type-1. From Type-1 to Type-6, the architecture progressively becomes more complete toward the necessary functions of autonomous mental development. Properties of each type are presented. Experiments are discussed with emphasis on their architectures. r 2007 Published by Elsevier B.V.

. Neuroscientists have identified a neural substrate of prediction and reward in experiments with primates. The so-called dopamine neurons have been shown to code an error in the temporal prediction of rewards. Similarly, artificial systems can "learn to predict" by the so-called temporal-difference (TD) methods. Based on the general resemblance between the effective reinforcement term of TD models and the response of dopamine neurons, neuroscientists have developed a TDlearning time-delay actor-critic neural model and compared its performance with the behavior of monkeys in the laboratory. We have used such a neural network model to learn to predict variable-delay rewards in a robot spatial choice task similar to the one used by neuroscientists with primates. Such architecture implementing TD-learning appears as a promising mechanism for robotic systems that learn from simple human teaching signals in the real world. Keywords: Learning robots, time-delay neural networks,...

Summary. – Education is a goal-oriented field. But if we want to treat education scientifically so we can accumulate, evaluate, and refine what we learn, then we must develop a theoretical framework that is strongly rooted in objective observations and through which different theoretical models of student thinking can be compared. Much that is known in the behavioral sciences is robust and observationally based. In this paper, I draw from a variety of fields ranging from neuroscience to sociolinguistics to propose an over-arching theoretical framework that allows us to both make sense of what we see in the classroom and to compare a variety of specific theoretical approaches. My synthesis is organized around an analysis of the individual’s cognition and how it interacts with the environment. This leads to a two level system, a knowledge-structure level where associational patterns dominate, and a controlstructure level where one can describe expectations and epistemology. For each level, I sketch some plausible starting models for student thinking and learning in physics and give examples of how a theoretical orientation can affect instruction and research. 1

In this talk I consider what physics can offer to students, both as physics majors and in other sciences. The recent increases in the technological character of the workplace appear likely to continue, leading to increasing numbers of individuals who should learn something about science. For many of these people, understanding the character of science, including learning new ways to think about and analyze the physical world, is an essential component of what they need to learn. In the next few years, we will need to figure out exactly what we can usefully teach them and how to do it effectively in the short time they are in a physics class. The critical information for this discussion comes from a careful consideration of what it means to think about and understand science and from careful observations of the actual thinking processes of incoming physics students.

Common variants underlying cognitive ability: further evidence for association between the SNAP-25 gene and cognition using a family-based study in two independent Dutch cohorts

Abstract not found

This excerpt is provided, in screen-viewable form, for personal use only by