Abstract: An information recognition circuit comprises a plurality of recognition processing units each composed of a neural network. Teacher signals and information signals to be processed are supplied to a plurality of the units, individually so as to obtain output signals by executing individual learning. Thereafter, the plural units are connected to each other so as to construct a large scale information recognition system. Further, in the man-machine interface system, a plurality of operating instruction data are prepared. An operator's face is sensed by a TV camera to extract the factors related to the operator's facial expression. The neural network analogizes operator's feeling on the basis of the extracted factors. In accordance with the guessed results, a specific sort of the operating instruction is selected from a plurality of sorts of the operating instructions, and the selected instruction is displayed as an appropriate instruction for the operator.

Abstract: An information recognition circuit comprises a plurality of recognition processing units each composed of a neural network. Teacher signals and information signals to be processed are supplied to a plurality of the units, individually so as to obtain output signals by executing individual learning. Thereafter, the plural units are connected to each other so as to construct a large scale information recognition system. Further, in the man-machine interface system, a plurality of operating instruction data are prepared. An operator's face is sensed by a TV camera to extract the factors related to the operator's facial expression. The neural network analogizes operator's feeling on the basis of the extracted factors. In accordance with the guessed results, a specific sort of the operating instruction is selected from a plurality of sorts of the operating instructions, and the selected instruction is displayed as an appropriate instruction for the operator.

Abstract: A model predictive control apparatus constructed in consideration of limit conditions of the process and also suitable for a multi-input/output system and an input device suitable for such a control apparatus are disclosed.The model predictive control apparatus includes an transformation unit for transforming the cost function and the limit condition to a conditional expression only relating to the manipulated variable. A suitable cost function parameter adjustment unit in which robustness is taken into consideration is provided. Alternatively, by designation of a response time constant, a weight corresponding thereto is calculated or determined to carry out evaluation of stability margin.In addition, the input device is adapted to carry out, through a picture on screen, setting or alteration of a predictive model or control parameters, etc. to be inputted, thus to suitably conduct setting while confirming it on the screen.