The Wisdom Wall

“perception is what deep learning does, and actually it only does a small part of perception. There's lots of parts of perception where we use our knowledge about the world that it doesn't capture. And then there are all these other things like common sense and planning, analogy, language, and reasoning, and deep…”

“deep learning is a better ladder for sure, but a better ladder doesn't necessarily get you to the moon.”

“if a typical person can do a mental task with less than one second of thought, and we can gather an enormous amount of data, of directly relevant data, we have a fighting chance. So long as the test data aren't too terribly different from the training data, and the domain doesn't change too much over time.”

“deep learning doesn't even really fully understand the relations between parts and wholes. Um, it certainly doesn't understand what a silhouette is, and it gets it wrong.”

“deep learning can't do what we call compositionality. It can't put ideas together.”

“There are a lot of different components to cognition, and so we have to have a hybrid model. There's just no way that one system is going to do all of these different things”

“But it's another thing if you import those same techniques into robots. If you have your robots doing reinforcement learning, which is basically trial and error learning, they start knocking over the furniture a 100,000 times, you're probably gonna send it back to the manufacturer.”

“these successes are examples of one thing. They're all examples of what a cognitive psychologist would call perceptual classification, and that's part of what we do as intelligent human beings, but it's not all that we do.”

“deep learning, it mostly cares about texture.”

“if we want to build machines that are as smart as people, we should start by studying small people.”

“People get very excited every time there's a new deep learning result. Um, but it's always the case of doing better on the high frequency data than the low frequency data.”

“So, where I think we should start looking for clues, in a nutshell, is children.”

“if you have human-level intelligence, you can make sense of that, but if you just memorize stuff off the web and do information retrieval, you could actually get stuck there.”

“We wanted Rosie the robot, and instead we got Roomba.”

“finance is really fundamentally a sparse data problem because The financial markets aren't stationary.”

“So the old traditions are much better at dealing with abstract knowledge The new traditions are much better at learning things quickly.”