In the presence of a heavy-tail noise distribution, regression becomes much more di cult. Traditional robust regression methods assume that the noise distribution is symmetric and...
In this work, we discuss practical methods for the assessment, comparison, and selection of complex hierarchical Bayesian models. A natural way to assess the goodness of the model...
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
We propose a Markov process model for spike-frequency adapting neural ensembles which synthesizes existing mean-adaptation approaches, population density methods, and inhomogeneou...
Eilif Mueller, Lars Buesing, Johannes Schemmel, Ka...
An ensemble of stochastic non-leaky integrate-and-fire neurons with global, delayed and excitatory coupling and a small refractory period is analyzed. Simulations with adiabatic ...