Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
According to the current standard model, neurons in lateral geniculate nucleus (LGN) operate linearly. There is, however, ample evidence that LGN responses are nonlinear. To accou...
Abstract—We present a silicon neuron with a dynamic, active leak that enables precise spike-timing with respect to a time-varying input signal. Our neuron models the mammalian bu...
A novel neural network model is described that implements context-dependent learning of complex sequences. The model utilises leaky integrate-and-fire neurons to extract timing inf...
We have explored the role of the interaction of slow and fast intracellular dynamics in generating precise spiking-bursting activity in a model of the heartbeat central pattern gen...