Journal du génie chimique et de la technologie des procédés
Libre accès

Abstrait

Artificial intelligence and deep learning

Vahid Reza Khazaie

The evolution of the integration of robots into our nowadays life is becoming more sensible. Humans possess an inherent ability of perception and cognition; while robots may have limitations as they may not recognize an object or a being. So, we need to build robots equipped with enough intelligence that they can cope with their tasks in many applications. On the other hand, artificial intelligence (AI) is used to describe machines that imitate "cognitive" functions of human mind, such as "learning. Artificial neural networks are inspired by the architecture of neurons in the human brain. More specifically, Deep learning is a subset of machine learning in artificial intelligence (AI) that has networks capable of learning from the data. It is an artificial intelligence function that mimics the workings of the human brain in processing data and creating patterns for use in decision making. In recent years, deep learning has arguably achieved tremendous success. In simple words, deep learning uses the composition of many nonlinear functions to model the complex dependency between input features and labels. Recent advances have greatly improved the performance of artificial intelligence (AI) in computer vision and natural language processing tasks; these advances can lead to better performances of robots equipped with artificial intelligence (AI) in their tasks.