This paper presents new theoretical results on the global exponential stability of recurrent neural networks with bounded activation functions and bounded time-varying delays in the presence of strong external stimuli. It is shown that the Cohen-Grossberg neural network is globally exponentially stable, if the absolute value of the input vector exceeds a criterion. As special cases, the Hopfiel...

We study the probabilistic generative models parameterized by feedforward neural networks. An attractor dynamics for probabilistic inference in these models is derived from a mean field approximation for large, layered sigmoidal networks. Fixed points of the dynamics correspond to solutions of the mean field equations, which relate the statistics of each unit to those of its Markov blanket. We ...

Based on the Halanay inequality lemma, this Letter derives a new sufficient condition for the globally exponential stability of the generalized Cohen–Grossberg neural networks with delays (GDCGNNs). The GDCGNN is quite general, and can describe several well-known neural networks with and without delays, including Hopfield and cellular neural networks. It is shown that the proposed sufficient co...