Building Machines That Learn and Think Like People by Josh Tenenbaum, et al

From the abstract of the paper, the authors argue that truly human-like learning and thinking machines will need to diverge from current engineering trends. Specifically, they propose that these machines should:

1. Build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems.
2. Ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned.
3. Harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. The authors suggest concrete challenges and promising routes towards these goals that combine the strengths of recent neural network advances with more structured cognitive models.