Google’s DeepMind is also going down the ‘imagination’ path
Just another quick self glorifying I told you so post. Wired reports that Google is also drawing on imagination as a means to improve their AI:
“What differentiates these agents is that they learn a model of the world from noisy sensory data, rather than rely on privileged information such as a pre-specified, accurate simulator. Imagination-based approaches are particularly helpful in situations where the agent is in a new situation and has little direct experience to rely on, or when its actions have irreversible consequences and thinking carefully is desirable over spontaneous action.”
More info on DeepMind’s blog.
The other AI imagination pioneer I mentioned a year back in the meantime secured $50 Mio in funding last week.
“The true sign of intelligence is not knowledge but imagination.” Albert Einstein