Methods and systems for artificial cognition
Methods, systems and apparatus that provide for perceptual, cognitive, and motor behaviors in an integrated system implemented using neural architectures. Components of the system communicate using artificial neurons that implement neural networks. The connections between these networks form representations—referred to as semantic pointers—which model the various firing patterns of biological neural network connections. Semantic pointers can be thought of as elements of a neural vector space, and can implement a form of abstraction level filtering or compression, in which high-dimensional structures can be abstracted one or more times thereby reducing the number of dimensions needed to represent a particular structure.
1. An artificial intelligence system comprising:
at least one interface hierarchy configured to receive an input of a high-dimensional representation and to compress the high-dimensional representation to generate a lower-dimensional representation of the input;
at least one processing module configured to receive the lower-dimensional representation and to generate a further representation;
at least one control point positioned in a communication path between the at least one interface hierarchy and the at least one processing module, each control point being modulatable between an enabled state in which data is permitted to flow through the control point and a disabled state in which data is inhibited from flowing through the control point; and
an action selection controller configured to control communication of the lower-dimensional representation and the further representation between the at least one interface hierarchy and the at least one processing module by modulating the at least one control point.
2. The system of claim 1 , wherein an additional interface hierarchy is configured to decompress the further representation to generate an additional high-dimensional representation, the additional high-dimensional representation usable to produce an output.
3. The system of claim 1 , wherein the at least one interface hierarchy is implemented using a neural network.
4. The system of claim 3 , wherein the neural network is a spiking neural network.
5. The system of claim 1 , wherein the at least one processing module is implemented using a neural network.
6. The system of claim 5 , wherein the neural network is a spiking neural network.
7. The system of claim 1 , wherein the action selection controller is implemented using a neural network.
8. The system of claim 7 , wherein the neural network is a spiking neural network.
9. The system of claim 1 , wherein the at least one interface hierarchy comprises one or more modules selected from the list consisting of a visual input module, a working memory module and a motor output module.
10. The system of claim 1 , wherein the at least one processing module comprises one or more modules selected from the list consisting of an information encoding module, a transform calculation module, a reward evaluation module, an information decoding module and a motor processing module.
11. The system of claim 1 , wherein the action selection controller comprises one or more hierarchical processing networks.
12. The system of claim 11 , wherein the one or more hierarchical processing networks have functions analogous to at least one anatomical structure of mammalian basal ganglia.
13. The system of claim 12 , wherein the at least one anatomical structure is selected from the group consisting of striatum, subthalmic nucleus, ventral striatum, globus pallidus externus, globus pallidus internus, substantia nigra pars reticulate, substantia nigra pars compacta, and ventral tegmental area.
14. The system of claim 1 , wherein at least one particular control point of the at least one control point is further modulatable to at least one intermediate state in which data is modified as it flows through that control point.