Some people say that abstract thinking, intuition, common sense, and understanding cause and effect are important to make AGI.

How important is learning to learn for the development of AGI?


Learning to learn (also known as meta-learning) is very important for the development of artificial general intelligence (AGI), given that one of the desirable and fundamental properties of an AGI is the adaptability to different environments and the ability to continually learn, and meta-learning can be used to achieve that.

Meta-learning is thus related to multi-task, continual (or lifelong) and transfer learning. There are several approaches to meta-learning, such as MAML, but there is usually a meta-learner and a learner.

In the paper Building Machines That Learn and Think Like People (2016), Marcin Andrychowicz et al. argue that truly human-like learning and thinking machines (or AGI) should

  1. build causal models of the world that support explanation and understanding

  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

Another person that thinks that meta-learning is important for the development of AGI is Ben Goertzel. See e.g. his article From Here to Human-Level Artificial General Intelligence in Four (Not All That) Simple Steps.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.