You can’t just look inside a deep neural network to see how it works. A network’s reasoning is embedded in the behavior of thousands of simulated neurons, arranged into dozens or even hundreds of intricately interconnected layers. The neurons in the first layer each receive an input, like the intensity of a pixel in an image, and then perform a calculation before outputting a new signal. These outputs are fed, in a complex web, to the neurons in the next layer, and so on, until an overall output is produced. Plus, there is a process known as back-propagation that tweaks the calculations of individual neurons in a way that lets the network learn to produce a desired output.
Mrs. Weston was very ready to say how attentive and pleasant a companion he made himself — how much she saw to like in his disposition altogether . He appeared to have a very open temper — certainly a very cheerful and lively one; she could observe nothing wrong in his notions, a great deal decidedly right...This was all very promising; and, but for such an unfortunate fancy for having his hair cut, there was nothing to denote him unworthy of the distinguished honour which [Emma’s] imagination had given him; the honour, if not of being really in love with her, of being at least ver y near it, and saved only by her own indifference — (for still her resolution held of never marrying) — the honour, in short, of being marked out for her by all their joint acquaintance.