This text explains the history and mechanics of multilayer neural networks, a type of artificial intelligence. It details how these networks, initially dismissed, became foundational to modern AI through the development of back-propagation, a learning algorithm. The text contrasts this subsymbolic approach with symbolic AI, highlighting the strengths and weaknesses of each and their eventual convergence in machine learning. The ascent of machine learning is linked to increased computing power and data availability, setting the stage for further AI advancements. Finally, the text discusses the ongoing debate regarding the optimal balance between symbolic and subsymbolic AI approaches.
