**List of Abbreviations**


*Brain-Inspired Spiking Neural Networks DOI: http://dx.doi.org/10.5772/intechopen.93435*

**7. Conclusion**

*Biomimetics*

thoughts and advance the field of neuroscience.

**Acknowledgements**

original research.

**List of Abbreviations**

AI artificial intelligence ANN artificial neural networks

NWTA normalized winner take all PSTH peri-stimulus-time histogram

STDP spike timing dependent plasticity

t-SNE t-distributed stochastic neighbor embedding

SNN spiking neural network

UL upper limit neuron WTA winner take all

BN Bayesian neuron BP STDP backpropagation-STDP

Ex excitor neuron LL lower limit neuron LTD long-term depression LTP long-term potentiation MW moving-window

SF step-forward

**94**

This chapter discussed several concepts and techniques, all of which are bio inspired. The case studies presented provide a strong basis to grasp the immense potential these algorithms provide in tackling the very complex problems of today, which were unimaginable without the advances in this field. This chapter specifically provided a beginner's guide to the field of spiking neural networks. It presented a brief overview of neuron biology and notes on popular artificial neuron models. Information representation as spikes and how to transduce real world data to spikes and vice-versa was discussed which is similar to how brain represents information. Several tools for spiking neural network modeling and evaluation were provided for wholistic understanding and for experimental evaluation of one's network models. A few case study examples are presented to understand the presented concepts and the scope of information presented in this chapter. This is an ongoing research and a very hot topic with substantially new concepts and discoveries being published every week. The motivation being the ability for machines to autonomously and efficiently perform tasks which were previously delegated to humans only along every aspect of our lives. This is a paradigm shift and research will continue to not only develop machine intelligence but also to understand the inner workings of our brains, our

This chapter represents fundamental knowledge for understanding spiking neural networks. Some of the text and images are adopted from the available research literature. Rest of the work represents authors original contributions along with the co-authors of the following research contributions [20, 38, 39, 43, 60, 62]. I am thankful for the support of Dr. Qinru Qiu from Syracuse University and her research group members specifically Amar Shrestha in contributing during the
