What We Learned From The Deep Learning Revolution

Terrence Sejnowski is a pioneer in the field of computational neuroscience and a long-time researcher of artificial neural networks. In an interview with TechTalks, Sejnowski discussed the early struggles of deep learning, its explosion into the mainstream, and the lessons learned from decades of research and development. Sejnowski became interested in artificial intelligence during the heyday of symbolic AI, which focused on hardcoding rules and knowledge into computers. Connectionist AI, which focuses on areas such as machine learning and artificial neural networks, was inspired by the biological structure of natural intelligence. Symbolic AI made quick progress on difficult logical problems, but connectionist AI has seen a resurgence in recent years due to its ability to learn representations of different things and concepts.