Conventional industrial control systems are in majority based on the single-input-single-output design principle with linearized models of the processes. However, most industrial p...
We distinguish between two main types of model: predictive and explanatory. It is argued (in the absence of models that predict on unseen data) that in order for a model to increas...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
A new model which can recognize rotated, distorted, scaled, shifted and noised patterns is proposed. The model is constructed based on psychological experiments in a mental rotatio...
Experimental data show that biological synapses behave quite differently from the symbolic synapses in common artificial neural network models. Biological synapses are dynamic, i....