Karen Hao analysed nearly 17,000 studies on artificial intelligence and wrote an article on where he believes AI is heading

• The biggest shift was the transition from expert systems (knowledge-based systems) to machine learning in the early 2000s. The term “logic” is increasingly less used in research, while words like “learning” and “data” are becoming more prevalent.
• Almost everything you hear today about artificial intelligence is thanks to deep learning. Neural networks are on the rise. Since 2012, when Geoffrey Hinton introduced a neural network that could recognise images with over 10% greater accuracy than other algorithms.
• The analysis revealed that the third trend emerging in research is reinforcement learning. A breakthrough occurred in 2015 when AlphaGo from DeepMind, using reinforcement learning, defeated the world champion in the ancient game of Go.

Source: https://www.technologyreview.com/…/we-analyzed-16625-pape…/…