A model with E-I balanced neurons [1]. The neural model showed self-organized criticality (SOC) [2][3], and I used it to do simple computing tasks. See demo.ipynb for a simple demo.
More about Liquid State Machine and Reservoir Computing: [4][5].
The project was supervised by .
[1] Vogels, T. P., & Abbott, L. F. (2005). Signal propagation and logic gating in networks of integrate-and-fire neurons. Journal of neuroscience, 25(46), 10786-10795.
[2] Wang, S. J., Ouyang, G., Guang, J., Zhang, M., Wong, K. M., & Zhou, C. (2016). Stochastic oscillation in self-organized critical states of small systems: Sensitive resting state in neural systems. Physical review letters, 116(1), 018101.
[3] Wang, S. J., Hilgetag, C., & Zhou, C. (2011). Sustained activity in hierarchical modular neural networks: self-organized criticality and oscillations. Frontiers in computational neuroscience, 5, 30.
[4] Lukoševičius, M., & Jaeger, H. (2009). Reservoir computing approaches to recurrent neural network training. Computer Science Review, 3(3), 127-149.
[5] Maass, W., & Markram, H. (2004). On the computational power of circuits of spiking neurons. Journal of computer and system sciences, 69(4), 593-616.