Vicarious is betting against the current trend in AI towards deep learning. Companies including Google, Facebook, Amazon, and Microsoft have made stunning progress in the past few years by feeding huge quantities of data into large neural networks in a process called “deep learning.” When trained on enough examples, for instance, deep-learning systems can learn to recognize a particular face or type of animal with very high accuracy. But those neural networks are only very crude approximations of what’s found inside a real brain.
Vicar artificiailious has introduced a new kind of neural-network algorithm designed to take into account more of the features that appear in biology. An important one is the ability to picture what the information it’s learned should look like in different scenarios—a kind of artificial imagination. The company’s founders believe a fundamentally different design will be essential if machines are to demonstrate more humanlike intelligence. Computers will have to be able to learn from less data, and to recognize stimuli or concepts more easily.
This year Vicarious will publish details of its research, and will have demos of what their systems involving robots.
Vicarious mathematical innovations, CEO Scott Phoenix says, more faithfully mimic the information processing found in the human brain. The relationship between the neural networks currently used in AI and the neurons, dendrites, and synapses found in a real brain is tenuous at best.
Vicarious has so far shown that its approach can create a visual system capable of surprisingly deft interpretation. In 2013 it showed that the system could solve any captcha (visual puzzles that are used to prevent spam-bots from signing up for e-mail accounts). As Phoenix explains it, the feedback mechanism built into Vicarious’s system allows it to imagine what a character would look like if it weren’t distorted or partly obscured
In an interview Scott Phoenix mentioned that their system can identify animals in clouds. It can look at clouds and say that it looks like a frog and then explain why it looks like a frog. It can say where it sees a frogs head or leg and then traces it out.