Noise in neural networks: thresholds, hysteresis, and neuromodulation of signal-to-noise.

AUTOR(ES)

Keeler, J D

RESUMO

We study a neural-network model including Gaussian noise, higher-order neuronal interactions, and neuromodulation. For a first-order network, there is a threshold in the noise level (phase transition) above which the network displays only disorganized behavior and critical slowing down near the noise threshold. The network can tolerate more noise if it has higher-order feedback interactions, which also lead to hysteresis and multistability in the network dynamics. The signal-to-noise ratio can be adjusted in a biological neural network by neuromodulators such as norepinephrine. Comparisons are made to experimental results and further investigations are suggested to test the effects of hysteresis and neuromodulation in pattern recognition and learning. We propose that norepinephrine may "quench" the neural patterns of activity to enhance the ability to learn details.

Documentos Relacionados

• The signal-to-noise characteristics of rod—cone interaction
• Estimation Uncertainties in the Optical Signal-to-Noise Ratio Network Optimization
• Noise injection for training artificial neural networks: A comparison with weight decay and early stopping
• Increase in signal-to-noise ratio of > 10,000 times in liquid-state NMR
• REGIME-SWITCHING MODELS: THRESHOLDS, SMOOTH TRANSITIONS, AND NEURAL NETWORKS