I have read the following https://www.technologyreview.com/s/604087/the-dark-secret-at-the-heart-of-ai/ and, again, I thought about the misinterpretation that Artificial Intelligence is going through.
Do your remember Visicalc? Probably not. Visicalc was the first spreadsheet, 20 rows by 5 column (!) by Dan Bricklin with Bob Frankston. It was 1978. The Spreadsheet! The tools that makes the world go around… You have a world before 1978 and a world after 1978. And the world after 1978 has transposed in the spreadsheet programs (now thousands of rows by thousands of columns, and in the cloud!) what they were used to do by hand.
Neural networks (the logical and computational engines of AI systems) are not so different from a spreadsheet. In effect, they are spreadsheets! And as spreadsheets, they get in raw data to output a result. Simply, neural networks contains the data and a relational tool that correlates the data, and this engine (the dark box) apply a reverse logic. Visical and all its children and nephews apply algebra to raw data and calculate the result. The neural networks do not calculate the exact result, they calculate the less improbable result, in the range of the previously given results. The two, often, coincide. It is, anyway, a statistic tool.
The logic of “less improbable” has demonstrated to be very effective in solving very complex problems, like image analysis, categorization of large amount of data, correlation of many different inputs. Neural networks are a powerful diagnostic tool: given symptoms, a range of possible deseases is restricted; or think to recognizing elements in an image, here they do real the magic: the neural networks can see. They can recognize fingerprints, faces, animals …
In the case of trading, the neural networks can provide an unbiased unique reading of the market.