Nonlinear adaptive filters based on a variety of neural network models have been used successfully for system identification and noise-cancellation in a wide class of applications. An important problem in data communications is that of channel equalization, i.e., the removal of interferences introduced by linear or nonlinear message corrupting mechanisms, so that the originally transmitted symbols can be recovered correctly at the receiver. In this paper we introduce an adaptive recurrent neural network (RNN) based equalizer whose small size and high performance makes it suitable for high-speed channel equalization. We propose RNN based structures for both trained adaptation and blind equalization, and we evaluate their performance via extensive simulations for a variety of signal modulations and communication channel models. It is shown that the RNN equalizers have comparable performance with traditional linear filter based equalizers when the channel interferences are relatively mild, and that they outperform them by several orders of magnitude when either the channel's transfer function has spectral nulls or severe nonlinear distortion is present. In addition, the small-size RNN equalizers, being essentially generalized IIR filters, are shown to outperform multilayer perceptron equalizers of larger computational complexity in linear and nonlinear channel equalization cases.

Parkinson’s disease and related synucleinopathies are characterized by the abnormal accumulation of alpha-synuclein aggregates, loss of dopaminergic neurons, and gliosis of the substantia nigra. Although clinical evidence and in vitro studies indicate disruption of the Blood-Brain Barrier in Parkinson’s disease, the mechanisms mediating the endothelial dysfunction is not well understood. Here we leveraged the Organs-on-Chips technology to develop a human Brain-Chip representative of the substantia nigra area of the brain containing dopaminergic neurons, astrocytes, microglia, pericytes, and microvascular brain endothelial cells, cultured under fluid flow. Our αSyn fibril-induced model was capable of reproducing several key aspects of Parkinson’s disease, including accumulation of phosphorylated αSyn (pSer129-αSyn), mitochondrial impairment, neuroinflammation, and compromised barrier function. This model may enable research into the dynamics of cell-cell interactions in human synucleinopathies and serve as a testing platform for target identification and validation of novel therapeutics.