"New Neural" is an Open Source neural network engine project for the MetaTrader 5 platform. - page 82

[Mykola Demko]

gpwr:

First, a little off-topic. There was such a project in Caltech, PolyWorld. The goal of the project was to create a two-dimensional world of virtual creatures, give them a simple brain-network, and the ability to see, move, find food, reproduce, kill each other (the amount of food is limited), etc. in order to survive. The brain-network consisted of several neurons with a given input-output function and plastic (learnable) synapses between neurons. At birth, the connections between neurons are random. The goal of the project was to observe the evolution of this virtual world. Those interested can watch a lecture about this project here (the interesting part starts at minute 16):

https://www.youtube.com/watch?v=_m97_kL4ox0

Now on to the subject. Has anyone tried to apply genetics to a network of neurons connected to each other, to inputs and outputs via initial-random weights? Synapses can appear and disappear by applying Hebb's rule or other unsupervised learning rule. Create a virtual world of such networks-traders trading forex, each having a certain initial deposit and trying to increase it at the expense of other traders. For example, every time when some trader makes a profitable deal, the profit flows from the funds of other traders, or something like that, but the total funds remain constant. Traders compete with each other for survival, i.e. not to drain the deposit. You can introduce the possibility of crossing network traders, etc. In short, create a real environment for the evolution of networks in the market.

I have such an idea after I wrote Life on mql4, and I've decided that it is necessary to try to write it when I'm familiar with echo, but I'm ready for the realization only now.

I just now see how to implement it.

[Mykola Demko]

TheXpert:
Cognitron and Hopfield. Oh and ok, the echo network )))

What's wrong with the cognitron?

I already wrote about hopfield.

The echo is just asking to be laid on top of this model.

Sorry to describe each model will break the bed, so if you do not understand how to implement, then ask specifically what in a particular network is difficult to implement, I'll try to paint.

[TheXpert]

Urain:

What's wrong with the cognitron?

There's nothing wrong with it. Have you seen the schematic?

Come on, there's no sense in stirring the air. The inconveniences will come out later, as soon as you start implementing it.

[Mykola Demko]

TheXpert:

There's nothing wrong with it. Have you seen the schematic?

Come on, there's no point in shaking the air. The inconvenience will come out later, as soon as you start to implement it.

Normal there, activation links inhibit connections, I do not see the difficulty.

Maybe I have a different diagram, show me?

You think that model that I presented can only summarize inputs?

in fact, what a neuron will do with inputs, is determined by a descendant of the CProcessing class,

for each type of neuron it can be different, you can also describe the processing of the cognitron.

[Konstantin Grebenshikov]

Wanted that the project is not stalled in the bud and started and developed huge steps forward as it is possible future of the whole project. I can't imagine the project without the following things:

1. the initial support of calculations by GPU for training or optimization of the neuronet and of course the cloud to support such as already exists.

2. Creating your own network emulator with a selection of the architecture and its training methods, etc. So that the user himself could choose the necessary method of creating his own strategy.

[Vladimir Gomonov]

All my attempts to embed video have failed. Just like trying to convert to .flv myself.

Eric Berlow: How complexity leads to simplicity.

http://www.ted.com/talks/lang/ru/eric_berlow_how_complexity_leads_to_simplicity.html

[Aleksey Rodionov]

MetaDriver:

http://www.ted.com/talks/lang/ru/eric_berlow_how_complexity_leads_to_simplicity.html

[Aleksey Rodionov]

MetaDriver:

All my attempts to embed video have failed. Just like trying to convert to .flv myself.

Eric Berlow: How complexity leads to simplicity.

http://www.ted.com/talks/lang/ru/eric_berlow_how_complexity_leads_to_simplicity.html

only from youtube is inserted (rules)

[Vladimir Gomonov]

Zeleniy:
only from youtube is inserted (rules)

Okay. Thank you.

[Alexey]

And also add the ability for neurons to be born and die. Just like between the ears.