The rapid progress of AI in the last few years is largely the result of advances in deep learning and neural nets, combined with the availability of large datasets and fast hardware for numerical computing (GPUs). We now have systems that can recognize images with an accuracy that rivals that of humans. This will lead to revolutions in several domains such as autonomous transportation, medical image analysis and personalized medicine. Similarly dramatic progress have been achieved in speech recognition, natural language understanding, and language translation. AI will profoundly transform society and cause major shifts in many industries. But all of the current systems are trained through supervised learning, where the machine is trained with inputs labeled by humans. To make significant progress in AI, researchers are working on new forms of learning where machines learn like humans and animals, learning how the world works and building predictive models of the world by observation and action. Will future autonomous machines ultimately acquire "common sense" and learn how to behave like humans and other animals? What will be their impact on society?
This lecture will be accessible to a general audience.
Back to New Deep Learning Techniques