Convergence in an Adaptive Neural Network: The Influence of Noise Inputs Correlation
This paper presents a study of convergence modalities in a small adaptive network of conductance-based neurons, receiving input patterns with different degrees correlation . The models for the neurons, synapses and plasticity rules (STDP) have a common biophysics basis. The neural network is simulated using a mixed analog-digital platform, which performs real-time simulations. We describe the study context, and the models for the neurons and for the adaptation functions. Then we present the simulation platform, including analog integrated circuits to simulate the neurons and a real-time software to simulate the plasticity. We also detail the analysis tools used to evaluate the final state of the network by the way of its post-adaptation synaptic weights. Finally, we present experimental results, with a systematic exploration of the network convergence when varying the input correlation, the initial weights and the distribution of hardware neurons to simulate the biological variability.
KeywordsNeuromorphic Engineering Silicon Neurons STDP Hodgkin-Huxley Model
Unable to display preview. Download preview PDF.
- 1.Hebb, D.O.: The Organization of Behaviour. John Wiley and Sons, Chichester (1949)Google Scholar
- 5.Daouzli, A., Saïghi, S., Buhry, L., Bornat, Y., Renaud, S.: Weights convergence and spikes correlation in an adaptive neural network implemented on vlsi. In: Proc.s of the Int. Conf. on Bio-inspired Systems and Signal Processing (BIOSIGNALS), pp. 286–291 (2008)Google Scholar
- 12.Renaud, S., Tomas, J., Bornat, Y., Daouzli, A., Saighi, S.: Neuromimetic ICs with analog cores: an alternative for simulating spiking neural networks. In: InternationaI Symposium on Circuits And Systems, pp. 3355–3358. IEEE, Los Alamitos (2007)Google Scholar