Additions and multiplications. People are making it sound like it's complicated, but NNs have the most basic and simple maths behind

The only thing is that nobody understand why they work so well. There are a few function approximation theorems that apply, but nobody really knows how to make them behave as we would like

So basically AI research is 5% "maths", 20% data sourcing and engineering, 50% compute power, and 25% trial and error

▲

amelius 5 days ago | parent | next [-]

Gradient descent is like pounding on a black box until it gives you the answers you were looking for. Ihere is little more we know about it. We're basically doing Alchemy 2.0.

The hard technology that makes this all possible is in semiconductor fabrication. Outside of that, math has comparatively little to do with our recent successes.

▲

p1dda 5 days ago | parent | prev [-]

> The only thing is that nobody understand why they work so well.

This is exactly what I have ascertained from several different experts in this field. Interesting that a machine has been constructed that performs better than expected and/or is performing more advanced tasks than the inventors expected.

	▲	skydhash 5 days ago \| parent [-]
		The linear regression model "ax + b" is the most simplest one and is still quite useful. It can be interesting to discover some phenomenon that fits the model, but that's not something people have control over. But imagine spending years (expensively) training stuff with millions of weight to ultimately discover it was as simple as "e = mc^2" (and c^2 is basically a constant, so the equation is technically linear)