Adaptron is a cognitive architecture that is designed to control the intelligent behaviour of robots. It uses compositional hierarchies of binary neurons (binons) as its representational system. Binons are general-purpose, relational and functional nodes for representing knowledge, concepts and abilities. Adaptron satisfies many of the important requirements for artificial general intelligence. These requirements are purposeful, grounded, autonomous, general-purpose, scalable and reliable. Experiments have shown that this architecture is effective for the recognition of handwritten digits and Morse code as well as for the control of a simulated robot in a maze environment. Adaptron interacts with its environment via senses and action devices. As it learns it builds up an integrated perception–action hierarchy of binons to represent its experiences. This mental model of its world is then used for thinking and rehearsing action outcomes. It is also used to control mental operations such as paying attention and selecting actions. Binons are used to perform all of these operations. A binon is a simple deterministic artificial neural node that represents a relationship. It has links to two lower nodes and is reused by zero or more upper nodes. Binons are general-purpose components that interact with each other like objects in object-oriented software. There are currently four types of binons. Name binons represent the category names for types of entities. Value binons are used to represent amodal property values such as position, intensity, time and quantity. Entity binons represent things and their types such as properties, objects, events and actions. Control binons are used to learn, manage and repeat behavioural and mental processes. Binons can also be subdivided based on what role they play. Recognition binons are used in perception and prediction. Action and expectation binons are used for behavioural control. They are equivalent to command neurons in neuroscience, production rules in cognitive science, or the forward and inverse models in motor control. And there are mental operation binons to focus attention, perform thinking and initiate actions. Adaptron starts with no knowledge or abilities. New binons are created and integrated with existing ones to represent everything it learns. Learning takes place in five stages: reflexes, babbling, reuse, practice and automaticity. Novel experiences result from reflexes and babbling. These experiences become familiar and are learnt through reuse. They become more reliable through practice and can be performed as automatic habits. This is consistent with the dual process theory of cognition.
If you are interested in reviewing the book, I can provide you with a draft version, one chapter at a time. The book currently has 10 chapters. The first chapter is a 12 page introduction and executive summary.
If you provide useful feedback on a chapter, I will send you the next chapter when it is ready.
Please respond by using Contact us below.