Deep learning is driving the explosion of artificial intelligence today. Deep learning—software that attempts to mimic activity in neurons in the neocortex—has greatly enhanced state-of-the-art techniques in speech recognition, natural language understanding, object detection, visual object recognition, and language translation.
Deep learning involves computational models composed of multiple processing layers in order to learn representations of data with several levels of abstraction. The layers thus discover intricate structure in large data sets. The key aspect of deep learning is that these layers are not designed by humans but are rather learned from data using a general-purpose learning procedure. The concept is making advances that have for long resisted artificial intelligence, is at the core of computer vision and auditory perception by computers, and is used in self-driving cars, social network content filtering, and search engine ranking.
Yann LeCun of New York University and Facebook researches artificial intelligence, machine learning, and deep learning. In the video above, he talks about deep learning’s impact on various disciplines ranging from artificial intelligence and imaging to biomedicine, drug discovery and genomics.