>>105815372
Can you calculate the local minima of mean squared error loss using a sigmoid function and multidimensional gradient descent? That is the difference between building the AI and being replaced by the AI.

>>16705424

>We are talking thousands of dimensions and calculating the derivstions of a "slice" of each dimension one at a time to make tiny adjustments.

Past three dimensions my mind can't conceptualize it. I can visualize the derivation of a 3D graph making steps to find local minima through linear regression. It is like a ball falling to a curve in a surface.

4D? What does that look like? 100+ dimensions? Just to draw a tiny image. I can only visualize the nodes. At this point the computer is thinking on a level the human brain just isn't capable of.

>>16700578

Things that writing neural networks for machine learning has taught me, coming from a background of calculus:

>Backpropagation
>Sigmoid function
>Partial derivatives
>Mean squared error
>Stochastic gradient descent
>Multidimensional linear regression

I will sit down and work through every part of the problem until I can wrap my head around it completely.

I especially like how partial derivatives are used to fine tune neural networks to local minima in functions that include thousands of dimensions.