چكيده لاتين :
This paper introduces a new structure in neural networks called TD-CMAC, an extension to the conventional
Cerebellar ModelArithmetic Computer (CMAC), having reasonable ability in time series prediction. TD-CMAC, the
conventionalCMAC and a classical neural network model called Multi-Layer Perceptron (MLP) are simulated and
evaluated for l-hour-ahead prediction and 24-hour-ahead prediction of carbon monoxide as one of primary air
pollutants. Carbon monoxide data used in this evaluation were recorded and averaged at Villa station in Tehran, Iran
from October3Td
• 2001 to March 14th 2002 at one-hour intervals. The results showthat the errors madebyTD-CMAC
is fewer than those made by other models.
