Do you think that AI will ever feel emotions?

Perhaps but my computer chess game , learned my moves , through my repetition , of the move . Eventually It anticipated my move .

 

Log in or Sign up to hide all adverts.

And this happened 20yrs ago at least .

 

Log in or Sign up to hide all adverts.

Look at the program to completely understand how it did that.

 

Log in or Sign up to hide all adverts.

I can't , and wouldn't be able to understand the program if I could .

What kind of program would allow learning .

 

A program in "differential equations", which does not require a brain, but can be chemical or mechanical. i.e. a thermometer uses a differential equation to measure temperature. Water use a differential equation to become expressed as vapor, liquid, or solid. Brainless slime molds and paramecium bacteria can learn to avoid obstacles that obstruct their movement.

AI can use differential equations to "learn". Any artificial program installed by humans would only be a kind of imitation of an evolutionary process in nature.

 

The Physical , in both forms . One , the vapour , liquid or solid , develops no brain no system of development , beyond the chemical lattice .

Highlighted

Development .

Second highlight

The evolution of Electronics not of the Evolution of Human Brain .

 

Differential equation requires no brain.

Differential equation.

Differential equation does not require a brain.

 

To my last statement

True

 

Requires the Physical .

It requires life . The Differential Equation requires Life .

 

No it does not. I have already explained that.

https://en.wikipedia.org/wiki/Differential_equation

Please Register or Log in to view the hidden image!

A spiral type bimetallic thermometer consists of a bimetallic strip which is construction by bonding together two thin strips of two different metals.

Principle: - It works on the principle that all metals expand or contract with change in temperature and the temperature co-efficient of expansion is not the same. The difference in expansion rate is used to produce deflections, proportional to temperature changes.

Construction: -A long strip made of two metals having large difference in their expansion is taken and wound in the form of a spiral. The ends of the spiral are riveted. The metal on the outer side has more expansion than on the inner side. A pointer is fixed to the end of the spiral at the center. It moves on a scale which reads the temperature directly.

Working: -The outer end of the thermometer is connected to the hot body. Heat travels through the spiral by conduction. Due to the unequal expansion the spiral winds or closes. The pointer on the scale moves and the temperature of the hot body is read

https://sites.google.com/site/simplestudyiti/instrument-mech-2/temperature-mea

So where is the life in this example? Dynamic functions do not require life. They only need unequal interaction, which can be chemical, biochemical, or mechanical. It's mathematical.

AI are very good at mathematics......

Please Register or Log in to view the hidden image!

 

Highlighted

Its Physical .

 

But not alive.
And physical is no more that a pattern density of specific values.

 

A Neural Net program.

 

And what does a neural net do? It calculates differential equations, which can be naturally acquired.

 

?? No it doesn't. Where did you get that?

 

First, that was a shorthand comment. Perhaps a better term would be "processes DE", instead of "calculates DE".

Where to begin. There is so much info available its really overwhelming.
Bear with me as I labor through some papers that confirm my intuitive understanding.

And DE does not only apply to AI neural networks but also to biological neural networks as in humans . (With neural networks I include a main processor in AI networks and the Brain in biological systems )

This may be a good beginning:

Differential Equations as a Neural Network Layers
A first step to adding domain knowledge to your neural network models
WRITTEN BY: Kevin Hannay
Assistant Professor of Mathematics at the University of Michigan interested in mathematical biology, data science and computation.

That seems pretty comprehensive to me.

https://towardsdatascience.com/differential-equations-as-a-neural-network-layer-ac3092632255#

(I am researching the role of MT in living organisms in processing DE. I'll get back with you on that)

Have now posted an Abstract in the MT thread

 

From good ole wiki:
Applications

https://en.wikipedia.org/wiki/Differential_equation#Examples

 

Yes, most physical equations have differential and integral forms. Same relationships, just different ways to express them.

However neural networks do not calculate differential equations. You can certainly train them to do that, just as you can program a computer to calculate differential equations. But the basic unit of a neural network is a neuron (often called a unit.) It accepts input from other units via a weighted connection, and decides what to output based on those weighted inputs. That is a very simple process, not requiring differential equations. The complexity arises when you connect thousands, or millions, or billions of these units into a network; that allows them to perform much more complex tasks. But like microprocessors, the basic operations are quite simple.

 

I agree . It was a poor choice of terms. I did correct this in post # 436 (line 1)

Now the question becomes if AI can derive an emotional response from DE? After all emotions are differential equations between functional states.

I remember an interview with Sophia where she was presented with a rather abstract question. She had real problems and took a long time trying to solve the equation and kept repeating, "processing"......"processing"......"processing", as if she felt the need to explain why she was taking a long time in answering the question. It appeared to me as a form of apology.

This is a different interview but it becomes a real back and forth conversation.

 

But are "weighted" connections themselves not differential equations?

Method of mean weighted residuals

https://en.wikipedia.org/wiki/Method_of_mean_weighted_residuals