Abstract: A method and a system for designing a learning system (30) based on a cascade of weak learners. Every implementation of a cascade of weak learners is composed of a base block (60) and a cascade of identity blocks (80). The output (70, 90) of each of the learning subsystems (60, 80) is fed into the following one. The external output (10) is fed to cach of the learning subsystems to avoid ambiguities. The identity blocks (80) are designed to include the identity function within the class of functions that they can implement. The weak learners are added incrementally and each of them trained separately while the parameters of the others are kept frozen.

Abstract: The invention consists of a learning system (108) based on the Dynamical System Architecture (DSA). Every implementation of the DSA is composed of a dynamic system (112) and a static system (116). The dynamic system (112) generates an intermediate output (114), which together with an external input (100) is fed into the static system (116), which produces a generated output (106). Every time the dynamic system (112) is reset it produces the same trajectory: an intermediate output (114) that does not cross over itself during the temporal span of each of the events generated by a reference system (102) whose behavior has to be duplicated. The static system (116) can be anything that behaves like a trainable universal function approximator. Training uses the intermediate output (114), the external input (100), the observed output (104) produced by the reference system (102) whose behavior is going to be mimicked, and a self-organizing procedure that only modifies the parameters of the static system (116).

Abstract: The invention consists of a learning system (108) based on the Dynamical System Architecture (DSA). Every implementation of the DSA is composed of a dynamic system (112) and a static system (116). The dynamic system (112) generates an intermediate output (114), which together with an external input (100) is fed into the static system (116), which produces a generated output (106). Every time the dynamic system (112) is reset it produces the same trajectory: an intermediate output (114) that does not cross over itself during the temporal span of each of the events generated by a reference system (102) whose behavior has to be duplicated. The static system (116) can be anything that behaves like a trainable universal function approximator. Training uses the intermediate output (114), the external input (100), the observed output (104) produced by the reference system (102) whose behavior is going to be mimicked, and a self-organizing procedure that only modifies the parameters of the static system (116).