1

## For example, if I have the following architecture:

- Each neuron in the hidden layer has a connection from each one in the input layer.
- 3 x 1 Input Matrix and a 4 x 3 weight matrix (for the backpropagation we have of course the transformed version 3 x 4)

But until now, I still don't understand what the point is that a neuron has 3 inputs (in the hidden layer of the example). It would work the same way, if I would only adjust one weight of the 3 connections.

But in the current case the information flows only distributed over several "channels", but what is the point?

With backpropagation, in some cases the weights are simply adjusted proportionally based on the error.

Or is it just done that way, because then you can better mathematically implement everything (with matrix multiplication and so on)?

Either my question is stupid or I have an error in my thinking and assume wrong ideas. Can someone please help me with the interpretation.

In tensorflow playground for example, I cut the connections (by setting the weight to 0), it just compansated it by changing the other still existing connection a bit more:

so in short, was it made so that it could be better represented mathematically? So as a unified model? Isn't there some document or something that takes up my question and maybe even explains a meaning? – iwab – 2020-07-29T16:19:18.293

I don't follow how you get from my answer to "better represented mathematically" and "a unified model". Please explain. – Dave – 2020-07-29T16:22:49.003

ahh, i read your answer a bit wrong at first, but you actually say that it would also work with one input, but i would still like to know why someone came up with this architecture. – iwab – 2020-07-29T16:26:32.207

Which architecture? – Dave – 2020-07-29T16:27:50.410

the architecture that each neuron in one layer is connected to each in the next. – iwab – 2020-07-29T16:29:05.603

It seems like you're the one who came up with it. – Dave – 2020-07-29T16:29:57.423

Let us continue this discussion in chat.

– Dave – 2020-07-29T16:31:25.830