作者: S. Garavaglia
DOI: 10.1109/IJCNN.1992.226940
关键词: Work (electrical) 、 Content-addressable storage 、 Artificial intelligence 、 Bidirectional associative memory 、 Microeconomics 、 Artificial neural network 、 Computer science 、 Productivity
摘要: Artificial neural networks can be applied to analyzing and understanding economic behaviour. Feedback networks, such as the bidirectional associative memory (BAM) network, are appropriate when agents make decisions based on other agents' behavior. In case presented, BAM weight matrix represents influence of group workers any one worker. Each X vector a specific worker's characteristics Y results given firm's work rules. It is shown that imposing more constraints polarized them into two extreme performance groups with an overall result reducing effort offered by poorer workers. The presence poor causes good harder. not conclusive replacing better increases productivity group. >