- An image content recognition system based on a deep neural network achieves an accuracy close to that of primates.
- Because these networks are based on neuroscientists’ current understanding of how the brain performs object recognition, the success of the latest networks suggest that neuroscientists have a fairly accurate grasp of how object recognition works.
Cue Michael Jordan: Each “neuron” [in a DNN] is really a cartoon. It’s a linear-weighted sum that’s passed through a nonlinearity. Calling that a neuron is clearly, at best, a shorthand. It’s really a cartoon. … We don’t know how [real] neurons learn. Is it actually just a small change in the synaptic weight that’s responsible for learning? That’s what these [DNN] are doing. In the brain, we have precious little idea how learning is actually taking place.