This is the “recipe for building intelligent machines” from Jeff Hawkins (On Intelligence, 2004).
“Start with a set of senses to extract patterns from the world. Our intelligent machine many have a set of sense that differ from a human’s, and may even “exist” in a world unlike our own.
So don’t assume that it has to have a set of eyeballs and a pair of ears. Next, attach to these senses an hierarchical memory system that works on the same principles as the cortex. We will then have to train the memory system much as we teach children. Over repetitive training sessions, our intelligence machine will build a model of its world as seen through its senses.
There will be no need or opportunity for anyone to program in the rules of the world, database, facts, or any of the high-level concepts that are the bane of artificial intelligence. The intelligent machine must learn via observation of its world, including input form an instructor when necessary.
Once our intelligent machine has created a model of its world, it can then see analogies to past experiences, make predictions of future events, propose solutions to new problems, and make this knowledge available to us.”