Abstract
Computations adapted from the interactions of neurons in the nervous system have the potential to be a strong foundation for building computers with cognitive functions including decision-making, generalization, and real-time learning. In this context, a proposed intelligent machine is built on nervous system mechanisms. As a result, the output and middle layer of the machine is made up of a population of pyramidal neurons and interneurons, AMPA/GABA receptors, and excitatory and inhibitory neurotransmitters. The input layer of the machine is derived from the retinal model. A machine with a structure appropriate to biological evidence needs to learn based on biological evidence. Similar to this, the PSAC (Power-STDP Actor-Critic) learning algorithm was developed as a new learning mechanism based on unsupervised and reinforcement learning procedure. Four datasets MNIST, EMNIST, CIFAR10, and CIFAR100 were used to confirm the performance of the proposed learning algorithm compared to deep and spiking networks, and respectively accuracies of 97.7%, 97.95% (digits) and 93.73% (letters), 93.6%, and 75% have been obtained, which shows an improvement in accuracy compared to previous spiking networks. The suggested learning strategy not only outperforms the earlier spike-based learning techniques in terms of accuracy but also exhibits a faster rate of convergence throughout the training phase.