Consciousness driven Spike Timing Dependent Plasticity

Spiking Neural Networks (SNNs), recognized for their biological plausibility and energy efficiency, employ sparse and asynchronous spikes for communication. However, the training of SNNs encounters difficulties coming from non-differentiable activation functions and the movement of spike-based inter-layer data. Spike-Timing Dependent Plasticity (STDP), inspired by neurobiology, plays a crucial role in SNN's learning. Various models of STDP are introduced in the literature with adaptability and integrability but they still lacks the conscious part of the brain used for learning. Considering the issue, this research work proposes a Consciousness Driven STDP (CD-STDP), an improved solution addressing inherent limitations observed in conventional STDP models. CD-STDP, designed to infuse the conscious part as coefficients of long-term potentiation (LTP) and long-term depression (LTD), exhibit a dynamic nature. The model connects LTP and LTD coefficients to current and past state of synaptic activities, respectively, enhancing consciousness and adaptability. The conscious coefficient adjustment in response to current and past synaptic activity extends the model's conscious and other cognitive capabilities, offering a refined and efficient approach for real-world applications. Evaluations on Modified National Institute of Standards and Technology (MNIST), FashionMNIST and California Institute of Technology (CALTECH) datasets showcase CD-STDP's remarkable accuracy of 98.6%, 85.61% and 99.0%, respectively, in a single hidden layer SNN. In addition, analysis of conscious elements and consciousness of the proposed model on SNN is performed.