Neural networks are one of the most popular and powerful classes of machine learning algorithms. In quantitative finance neural networks are often used for time-series forecasting, constructing proprietary indicators, algorithmic trading, securities classification and credit risk modeling. They have also been used to construct stochastic process models and price derivatives. Despite their usefulness neural networks tend to have a bad reputation because their performance is “temperamental”. In my opinion this can be attributed to poor network design owing to misconceptions regarding how neural networks work. This article discusses some of those misconceptions. Source
By Kasabov, Nikola
Artificial Intelligence (AI) is an interdisciplinary science area that develops and implements methods and systems that manifest cognitive behavior. Main features of AI are: learning,adaptation, generalization, inductive and deductive reasoning, human like communication in a natural language, etc. [1e8]. Some more features that are currently being developed include consciousness, self-assembly, selfreproduction, and social networks. Human cognitive behavior is based on knowledge that is evolving with time, always changing, improving, to ensure that we survive and do better. And evolving is expected to be its representation in AI.
AI has a long history of development and one cannot understand it or further develop it, if they do not understand and embrace the rich set of methods AI developed over a long time. Many of these methods are used in the current AI development and will be used in the future to come, in different ways of course. In the beginning, there was a school of learning that assumed that understanding of nature and its knowledge representation and articulation would not change with time. Aristotle was perhaps the most pronounced philosopher and encyclopedist of this school...
...
Aristotle introduced epistemology, which is based on the study of particular phenomena which leads to the articulation of knowledge (rules, formulas) across sciences: botany, zoology, physics, astronomy, chemistry, meteorology, psychology, etc. . According to Aristotle, this knowledge was not supposed to change. In places, Aristotle went too far in deriving “general laws of the universe” from simple observations and overstretched the reasons and conclusions. Because the was perhaps the philosopher most respected by European thinkers during and after the Renaissance, these thinkers, along with institutions, often took Aristotle’s erroneous positions, such as inferior roles of women, which held back science and social progress for a long time...
Download Full Article
Source
0 Comments