Developing an AI system capable of understanding natural language isn’t just time-consuming — it’s really expensive. Developers have to collect thousands of voice samples and annotate them by hand, a process that often takes weeks. That’s why researchers at Amazon’s Alexa division pursued transfer learning, which leverages a neural network — i.e., layers of mathematical functions that mimic neurons in the brain — trained on a large dataset of previously annotated samples to bootstrap training in a

Read More At Article Source | Article Attribution