[sushirain]

For example, ResNet from 2015 had 152 layers.

A real neuron takes in the order of 10ms to integrate and fire to the next neuron. Many subconscious reactions take less than 1 sec, which leaves time to a chain of length less than 100. Note that those neurons are not strictly arranged in layers.

The human visual cortex has 10^12 synapses [1]. One popular 2015 deep learning net (ResNet 152-layers) used 10^12 FLOPs to classify objects in one image (but less weights.)

In terms of depth, we're there. In terms of breadth, it will take several years. But the brain does things very differently. For example, it has top-down signals during "prediction."

[1] http://www.ncbi.nlm.nih.gov/pubmed/7244322

[visarga]

It would seem that the current release from FB does top-down and bottom-up integration:

> To capture general object shape, you have to have a high-level understanding of what you are looking at (DeepMask), but to accurately place the boundaries you need to look back at lower-level features all the way down to the pixels (SharpMask).

[tkinom]

"It will take several years."

A Noob question:

If it reaches the "breadth" of human brain, how close will that to the "Skynet becomes self-aware" moment.

What would it tell us about human, our society after it study, analyze millions, billions hours of FB, youtube videos?

[visarga]

As long as we do simple data processing, it won't become the dreaded Skynet. When we stuck a Reinforcement Learning system on top, feed it with reward signals and let it loose on the net or in real life robots, then it could become intelligent and develop its own goals/interests. So the Skynet part comes after reinforcement learning.