Artificial intelligence (AI) has a history of nearly a century from its inception to the present day. We have summarized the development trends and discovered universal rules, including both success and failure. We have analyzed the reasons from both technical and philosophical perspectives to help understand the reasons behind the past failures and current successes of AI, and to provide a basis for thinking and exploring future development. Specifically, we have found that the development of AI in different fields, including computer vision, natural language processing, and machine learning, follows a pattern from rules to statistics to data-driven methods. In the face of past failures and current successes, we need to think systematically about the reasons behind them. Given the unity of AI between natural and social sciences, it is necessary to incorporate philosophical thinking to understand and solve AI problems, and we believe that starting from the dialectical method of Marx is a feasible path. We have concluded that the sustainable development direction of AI should be human-machine collaboration and a technology path centered on computing power. Finally, we have summarized the impact of AI on society from this trend.

Equiangular lines are lines in space that pass through a single point, and whose pairwise angles are all equal. Mathematicians are not limited to three dimensions, however. "In high dimensions, things really get interesting, and the possibilities can seem limitless," says Yufei Zhao, assistant professor of mathematics. But they aren't limitless, according to Zhao and his team of MIT mathematicians, who sought to solve this problem on the geometry of lines in high-dimensional space. It's a problem that researchers have been puzzling over for at least 70 years. Their breakthrough determines the maximum possible number of lines that can be placed so that the lines are pairwise separated by the same given angle.

Using a machine learning technique, a team of Instituto de Astrofísica e Ciências do Espaço researchers constrained the radius of an exoplanet with known mass. Solène Ulmer-Moll, a Ph.D. student at the Science Faculty of the University of Porto (FCUP), explains this result was obtained by using knowledge from different fields: "This novel way to forecast exoplanet radius is a perfect example of the synergy between exoplanet science and machine learning techniques." To characterize a planet, both its mass and radius are needed in order to find the planet's density, and from that, to infer its composition. But both data are only available for a reduced number of exoplanets, since the mass is often determined by radial velocity measurements, while radius is measured with the transit method. The team developed an algorithm that accurately forecasts the radius of a wide range of exoplanets, if several other planetary and stellar parameters are known, including the exoplanet's mass and equilibrium temperature.

This algorithm uses supervised learning methods for training Artificial Neural Networks. The whole idea of training multi-layer perceptrons is to compute the derivatives of the error function or gradient descent with respect to weights using the backpropagation algorithm. This algorithm is actually based on the linear algebraic operation with a goal of optimising error function by harnessing its intelligence and provisioning updates. In this post, we will focus on backpropagation and basic details around it on a high level in simple English. As mentioned above "Backpropagation" is an algorithm which uses supervised learning methods to compute the gradient descent (delta rule) with respect to weights.

Thcsc are the problems of investigating theories and techniques of natural and artificial psychologies by means of t,he most fit mathematical concepts. Rational psychology should not, be confused with logic-based presentations of artificial intelligence. While investigations based on mathematical logic are relatively familiar and certainly useful, using only that portion of mathematics to characterize psychologies presupposes that psychological questions are fundamentally logical. That presupposition is not, ncccssary for the development of an exact science of mind. Rational Psychology Hat,ional psychology is a part of mathematics, the conceptual investigation of psychology.

If you imagine the life of a machine learning researcher, you might think it's quite glamorous. You'll program self-driving cars, work for the biggest names in tech, and your software could even lead to the downfall of humanity. But, as a new survey of data scientists and machine learners shows, those expectations need adjusting, because the biggest challenge in these professions is something quite mundane: cleaning dirty data. This comes from a survey conducted by data science community Kaggle (which was acquired by Google earlier this year). Some 16,700 of the site's 1.3 million members responded to the questionnaire, and when asked about the biggest barriers faced at work, the most common answer was "dirty data," followed by a lack of talent in the field.

As the field of "big data" has emerged as a tool for solving all sorts of scientific and societal questions, one of the main challenges that remains is whether, and how, multiple sets of data from various sources could be combined to determine cause-and-effect relationships in new and untested situations. Now, computer scientists from UCLA and Purdue University have devised a theoretical solution to that problem. Their research, which was published this month in the Proceedings of the National Academy of Sciences, could help improve scientists' ability to understand health care, economics, the environment and other areas of study, and to glean much more pertinent insight from data. The study's authors are Judea Pearl, a distinguished professor of computer science at the UCLA Henry Samueli School of Engineering and Applied Science, and Elias Bareinboim, an assistant professor of computer science at Purdue University who earned his doctorate at UCLA. Big data involves using mountains and mountains of information to uncover trends and patterns.

Let's say you're trying to pinpoint when a particular past event occurred, but your best possible estimate puts it only within a span of 10,000 years. Now imagine if something could shrink that window of "when" to just 30 years. That's the power of a new mathematical tool devised and tested by an international team of scientists, led by two from the University of Wisconsin-Milwaukee. The tool, a machine-learning algorithm honed by Abbas Ourmazd and Russell Fung, reduces timing uncertainties during changing events, improving accuracy by a factor of up to 300. It could have numerous applications, from dating past climate-change events with better precision to determining when molecular bonds form or break during chemical reactions lasting only a few quadrillionths of a second.