Deep learning is causing revolutions in computer perception and natural language understanding. But almost all these successes largely rely on supervised learning, where the machine is required to predict human-provided annotations. For game AI, most systems use model-free reinforcement learning, which requires too many trials to be practical in the real world. But animals and humans seem to learn vast amounts of knowledge about how the world works through mere observation and occasional actions. Good predictive world models are an essential component of intelligent behavior: with them, one can predict outcomes and plan courses of actions. One could argue that prediction is the essence of intelligence. Good predictive models may be the basis of intuition, reasoning and “common sense”, allowing us to fill in missing information: predicting the future from the past and present, the past from the present, or the state of the world from noisy percepts. After a brief presentation of the state of the art in deep learning, some promising principles and methods for predictive learning will be discussed.
This lecture will be accessible to a general scientific audience.