Recently we proposed a new neural network called Neural Tree Networks (NTN). The NTN is a combination of decision trees and multilayer perceptrons (MLP). The NTN grows the network as opposed to MLPs. The learning algorithm for growing NTNs is more efficient than standard decision tree algorithms. Simulation results have shown that the NTN is superior in performance to both decision trees and MLPs. In this paper a new NTN learning algorithm is proposed based on the thermal perception algorithm. It is shown that the new algorithm greatly increases the speed of learning of the NTN and attains similar classification performance as the previously used algorithm.