6
$\begingroup$

One question that came up learning how artificial neural networks are working was how the brain can train its neural network?

When we say we have an artificial neural network, the problem behind it is a typical, but uncommon minimizing problem. The math behind it is logical and pretty easy. But it's math, so an computer can calculate it by doing millions of iterations. But the brain can't do that (I would be surprised)

So, how does the brain solve this task. Trial & Error, we don't know or is there an even more complex system behind it?

Thanks in advance. GA

$\endgroup$
7
  • 1
    $\begingroup$ I'm voting to close this question as off-topic because it belongs on Cognitive Sciences S.E. $\endgroup$
    – AMR
    Jan 7, 2016 at 21:45
  • 1
    $\begingroup$ @AMR - not more on topic there than here. Wouldn't migrate. Wouldn't close here either. $\endgroup$
    – AliceD
    Jan 7, 2016 at 22:06
  • $\begingroup$ @Christiaan This really isn't asking about a purely biological process. Sure you could talk about reinforcing neuronal connections through repeated usage and the underlying chemistry, but that doesn't get at the learning aspect, and I think that the mechanisms of learning are Cog Sci more than straight biology. $\endgroup$
    – AMR
    Jan 7, 2016 at 22:12
  • 1
    $\begingroup$ @AMR a close vote based on too broad would be perfectly acceptable to me for sure. I just wouldn't like to see this migrated. $\endgroup$
    – AliceD
    Jan 7, 2016 at 22:20
  • 1
    $\begingroup$ this is one of the biggest open questions of the AGI field, a solution apparently nearly leads to AGI. there is some research trying to link gradient descent to brain neurology. also jeff hawkins postulates cortical columns are representing ML algorithms. Deepmind has some research relating to the hippocampus. may try to cook up some survey at some pt, but its an extremely challenging area to cite/ summarize current knowledge. the dopamine system has a lot to do with human rewards & presumably plays a large role. etc $\endgroup$
    – vzn
    Jun 7, 2018 at 16:57

1 Answer 1

4
$\begingroup$

The answer to this question is probably Hebbian Learning.

Hebbian learning can be nicely summarised with "Cells that fire together, wire together". So basically the synapses of neurons are strengthened if they fire in sync, and weakened otherwise.

One can easily see that a) this kind of local learning mechanism makes a lot more sense for the brain then some global method like gradient descent and b) this mechanism leads to stable representations of patterns.

In artificial neural networks this kind of learning is modelled in Hopfield networks and Restricted Boltzmann Machines.

Of course this simple rule barely scratches at the surface of what goes on in the human brain, when we are learning something. A complete picture would probably involve complex feedback mechanisms of inhibitory and excitatory connections between neurons, functional modules of neurons, and different parts of the brain.

But I fear these details are not yet well understood …

$\endgroup$
1
  • $\begingroup$ Oh. MY. GOD. I didn't through anybody would ever answer on this question anymore. :D Thx. $\endgroup$ Mar 19, 2016 at 3:20

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .