A Reward Driven Connectionist Model of Cognitive Development

Journal of Child Psychology and Psychiatry, 1997

What features of brain processing and neural development support linguistic and cognitive development in young children? To what extent are the profile and timing of development in young children determined by a preordained genetic programme? Does the environment play a crucial roic in determining the patterns of change observed in children growing up? These questions have been of central concern to developmental psychologists for well over a century. Yet none of them have received answers that are generally accepted by the profession. This article reviews some recent computational modelling of developmental change in children that promises to contribute to a deeper understanding ofthe issues behind these questions. The modelling work exploits artificial neural networks that mimic some of the basic properties of neural processing in the brain. These networks involve densely connected webs of simple processing units that propagate and transform complex patterns of activity. When exposed to a training environment, they undergo a process of selforganisation, yielding information processing systems that support new forms of behaviour. The study of the dynamics of these systems and their learning capabilities promises to provide us with important clues as to the nature of the mechanisms underlying development in infants and young children.

Artificial neural networks can model cortical local learning and signal processing, but they are not the brain, neither are many special purpose systems to which they contribute. Autonomous mental development models all or part of the brain (or the central nervous system) and how it develops and learns autonomously from infancy to adulthood. Like neural network research, such modeling aims to be biologically plausible. This paper discusses why autonomous development is necessary according to a concept called task muddiness. Then it introduces recent results for a series of research issues, including the new paradigm for autonomous development, mental architectures, developmental algorithm, a refined classification of types of machine learning, spatial complexity and time complexity. Finally, the paper presents some experimental results for applications, including: visionguided navigation, object finding, object-based attention (eye-pan), and attention-guided pre-reaching, four tasks which infants learn to perform early but very perceptually challenging for robots.

How have connectionist models informed the study of development? This paper considers three contributions from specific models. First, connectionist models have proven useful for exploring nonlinear dynamics and emergent properties, and their role in nonlinear developmental trajectories, critical periods and developmental disorders. Second, connectionist models have informed the study of the representations that lead to behavioral dissociations. Third, connectionist models have provided insight into neural mechanisms, and why different brain regions are specialized for different functions. Connectionist and dynamic systems approaches to development have differed, with connectionist approaches focused on learning processes and representations in cognitive tasks, and dynamic systems approaches focused on mathematical characterizations of physical elements of the system and their interactions with the environment. The two approaches also share much in common, such as their emphasis on continuous, nonlinear processes and their broad application to a range of behaviors.

Trends in cognitive …, 2006

2000

2004

We have recently shown that when initiated with "small" weights, many connectionist models with feedback connections are inherently biased towards Markov models, i.e. even prior to any training, dynamics of the models can be readily used to extract finite memory machines . In this study we briefly outline the core arguments for such claims and generalize the results to recursive neural networks capable of processing ordered trees. In the early stages of learning, the compositional organization of recursive activations has a Markovian structure: Trees sharing a top subtree are mapped close to each other. The deeper is the shared subtree, the closer are the trees mapped.

International journal of comparative …, 2005

Researchers within the field of learning have traditionally divided their empirical world according to methodology, with phenomena classified as single stimulus learning, Pavlovian conditioning, or in- strumental learning. This trichotomy, a vestige of our behaviorist past, continues to influence the field, both in the classroom and in the laboratory. Relying on data collected using a simple model system (learning within

Frontiers in neurorobotics, 2012

The recent outburst of interest in cognitive developmental robotics is fueled by the ambition to propose ecologically plausible mechanisms of how, among other things, a learning agent/robot could ground linguistic meanings in its sensorimotor behavior. Along this stream, we propose a model that allows the simulated iCub robot to learn the meanings of actions (point, touch, and push) oriented toward objects in robot’s peripersonal space. In our experiments, the iCub learns to execute motor actions and comment on them. Architecturally, the model is composed of three neural-network-based modules that are trained in different ways. The first module, a two-layer perceptron, is trained by back-propagation to attend to the target position in the visual scene, given the low-level visual information and the feature-based target information. The second module, having the form of an actor-critic architecture, is the most distinguishing part of our model, and is trained by a continuous version of reinforcement learning to execute actions as sequences, based on a linguistic command. The third module, an echo-state network, is trained to provide the linguistic description of the executed actions. The trained model generalizes well in case of novel action-target combinations with randomized initial arm positions. It can also promptly adapt its behavior if the action/target suddenly changes during motor execution.

… models of learning, development and evolution …, 2001

Behavioral and Brain Sciences, 1990

Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and “simple” homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models of memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities (including “distributed representations”) or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explo...