Skip to Main Content
A two-layer discrete-time neural net (NN) controller is presented for the control of an mnth order multi-input and multi-output (MIMO) dynamical system, so that linearity in the parameters holds, but the 'net reconstruction error' is considered to be nonzero. The NN controller exhibits learning-while-functioning-features instead of learning-then-control so that control is immediate with no explicit learning phase is needed. The structure of the NN controller is derived using a filtered error notion. It is indicated that delta rule-based weight tuning, when employed for closed-loop control, can yield unbounded NN weights if: (1) the net cannot exactly reconstruct a certain required function, or (2) there are bounded unknown disturbances acting on the dynamical system. A novel improved weight tuning algorithm is proposed to overcome the above problems.