Random neural network

A random neural network (RNN) is a mathematical representation of an interconnected network of neurons or cells which exchange spiking signals. It was invented by Erol Gelenbe and is linked to the G-network model of queueing networks which Erol Gelenbe also invented, and with his Gene Regulatory Network models. In this model, each neuronal cell state is represented by an integer whose value rises when the cell receives an excitatory spike and drops when it receives an inhibitory spike. The spikes can originate outside the network itself, or they can come from other cells in the networks. Cells whose internal excitatory state has a positive value are allowed to send out spikes of either kind to other cells in the network according to specific cell-dependent spiking rates. The model has a mathematical solution in steady-state which provides the joint probability distribution of the network in terms of the individual probabilities that each cell is excited and able to send out spikes. Computing this solution is based on solving a set of non-linear algebraic equations whose parameters are related to the spiking rates of individual cells and their connectivity to other cells, as well as the arrival rates of spikes from outside the network. The RNN is a recurrent model, i.e. a neural network that is allowed to have complex feedback loops.

A highly energy-efficient implementation of random neural networks was demonstrated by Krishna Palem et al. using the Probabilistic CMOS or PCMOS technology and was shown to be c. 226–300 times more efficient in terms of Energy-Performance-Product.

Random neural networks, like other artificial neural networks, have gradient-based learning algorithms. The learning algorithm for an n-node random neural network that includes feedback loops (it is also a recurrent neural network) is of computational complexity O(n^3) (the number of computations is proportional to the cube of n, the number of neurons). They can also be used with other learning algorithms such as reinforcement learning, and it has been shown to be a universal approximator for bounded and continuous functions.

The recurrent Random neural network was introduced by Erol Gelenbe (1989) based on the stochastic spiking behaviour of mammalian brain neurons . It was proved to have a convergent stable state, allowing the development of a simple deep learning gradient algorithm for this recurrent model . Its numerous applications include texture-based brain tumor detection from MR images and real-time deep learning-based video compression . Its reinforcement learning algorithm allows it to be used for packet network routing interoperably with the Internet protocol .

New developments of the Random neural network withdense clusters of recurrent neurons and Deep Learning, offer accurate algorithms for cyberattack detection and mitigation for computer networks and systems such as the Internet of Things , as well as for the real-time control of smart homes and power control


See also

References and sources

References
  1. ↑ Erol Gelenbe. "Random Neural Networks with Negative and Positive Signals and Product form Solution". Neural Computation, Vol. 1, No. 4, pp. 502-510, 1989, MIT Press.
  2. ↑ Erol Gelenbe. "Learning in the recurrent random neural network" (PDF). Neural Computation, Vol. 5, No. 1, pp. 154–164, 1993, MIT Press.
  3. ↑ Lakshmi N. Chakrapani; Bilge E. S. Akgul; Suresh Cheemalavagu; Pinar Korkmaz; Krishna V. Palem; Balasubramanian Seshasayee. "Ultra Efficient Embedded SOC Architectures based on Probabilistic CMOS (PCMOS) Technology". Design Automation and Test in Europe Conference (DATE), 2006.
  4. ↑ Gelenbe, Erol (1989). "Random neural networks with positive and negative signals and product form solution". Neural Computation. 1 (4): 505–510. doi:10.1162/neco.1989.1.4.502.
  5. ↑ Gelenbe, Erol (1990). "Stablility of the Random Neural Network". Neural Computation. 2 (2): 239–247. doi:10.1162/neco.1990.2.2.239.
  6. ↑ Gelenbe, Erol (1993). "Learning in the Recurrent Random Neural Network". Neural Computation. 5 (1): 154-164. doi:10.1162/neco.1993.5.1.15.
  7. ↑ Gelenbe, Erol; Feng, Yutao; Krishnan, Ranga R. (1996). "Neural network methods for volumetric magnetic resonance imaging of the human brain". Proceedings of the IEEE. 84 (10): 1488–1496. doi:10.1109/5.53711.
  8. ↑ Cramer, Christopher; Gelenbe, Erol; Bakircioglu, Hakan (1996). "Low bit-rate video compression with neural networks and temporal subsampling" (PDF). Proceedings of the IEEE. 84 (10): 1529–1543. doi:10.1109/5.537116.
  9. ↑ US patent 6804201, S. Erol Gelenbe, "Cognitive packet network", issued October 12, 2004
  10. ↑ Gelenbe, Erol (2009). "Steps towards self-aware networks". Communications of the ACM. 52 (7): 66–75. doi:10.1145/1538788.1538809.
  11. ↑ Gelenbe, Erol; Gul, Baran Can; Nakip, Mert (2025). "DISFIDA: Distributed Self-Supervised Federated Intrusion Detection Algorithm with Online Learning for Health Internet of Things and Internet of Vehicles". Internet of Things (Elsevier). 28 (101340).
  12. ↑ Gelenbe, Erol; Nasereddin, Mohammed (2025). "Adaptive attack mitigation for IoT flood attacks". IEEE Internet of Things Journal. 12 (5): 4701–4714. doi:10.1109/JIOT.2025.3529615.
  13. ↑ Adeel, Ahsan; Larijani, Hadi; Ahmadinia, Ali (2016). "Random neural network based novel decision making framework for optimized and autonomous power control in LTE uplink system". Physical Communication. 19: 106–117. doi:10.1016/j.phycom.2015.11.004.
Sources