Do you think that AI will ever feel emotions?

[river]

Computers will write code if the Programmers program them to do that. Computers are not going to do that "By themselves". It's always an algorithm in the Code.

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

 

[river]

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

And this happened 20yrs ago at least .

 

[Steve Klinko]

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

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

 

[river]

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

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

What kind of program would allow learning .

 

[Write4U]

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.

 

[river]

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 .

 

[Write4U]

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

Differential equation requires no brain.

Development

Differential equation.

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

Differential equation does not require a brain.

 

[river]

Write4U said: ↑
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 .

To my last statement

True

 

[river]

Differential equation requires no brain. Differential equation. Differential equation does not require a brain.

Requires the Physical .

It requires life . The Differential Equation requires Life .

 

[Write4U]

The evolution of Electronics not of the Evolution of Human 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.

In mathematics, a differential equation is an equation that relates one or more functions and their derivatives.[1]

In applications, the functions generally represent physical quantities, the derivatives represent their rates of change, and the differential equation defines a relationship between the two. Such relations are common; therefore, differential equations play a prominent role in many disciplines including engineering, physics, economics, and biology.

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

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......

 

[river]

No it does not. I have already explained that.
https://en.wikipedia.org/wiki/Differential_equation

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......

Highlighted

Its Physical .

 

[Write4U]

Its Physical

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

 

[Steve Klinko]

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

What kind of program would allow learning .

A Neural Net program.

 

[Write4U]

A Neural Net program.

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

 

[billvon]

And what does a neural net do? It calculates differential equations . . . .

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

 

[Write4U]

?? 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.

Thus, we can use a differential equation as a layer in a neural network. This is really neat for a few reasons:

Differential equations are the fundamental language of all physical laws.

That seems pretty comprehensive to me.

1. Outside of physics and chemistry differential equations are an important tool in describing the behavior of complex systems. Using differential equations models in our neural networks allows these models to be combined with neural networks approaches.
2. Building effective neural networks involves choosing a good underlying structure for the network. It is often easier to think of describing how a function changes in time, then it is to write down a function for the phenomena. Relatively simple rate laws can turn into very complex behavior (see the Lorenz system below!).

For simplicity, in this article, I am going to focus on neural networks with a single differential equations based layer in this article. However, these layers could easily be embedded as one layer in a deep learning project. The combination of deep learning with domain knowledge in the form of a differential equation is a game-changer in many fields.

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

 

[Write4U]

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

From good ole wiki:
Applications

The study of differential equations is a wide field in pure and applied mathematics, physics, and engineering. All of these disciplines are concerned with the properties of differential equations of various types.

Pure mathematics focuses on the existence and uniqueness of solutions, while applied mathematics emphasizes the rigorous justification of the methods for approximating solutions.

Differential equations play an important role in modeling virtually every physical, technical, or biological process, from celestial motion, to bridge design, to interactions between neurons. Differential equations such as those used to solve real-life problems may not necessarily be directly solvable, i.e. do not have closed form solutions. Instead, solutions can be approximated using numerical methods.

Many fundamental laws of physics and chemistry can be formulated as differential equations. In biology and economics, differential equations are used to model the behavior of complex systems. The mathematical theory of differential equations first developed together with the sciences where the equations had originated and where the results found application. However, diverse problems, sometimes originating in quite distinct scientific fields, may give rise to identical differential equations.

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

 

[billvon]

"Differential equations are the fundamental language of all physical laws."

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.

 

[Write4U]

However neural networks do not calculate differential equations.

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

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

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.

 

[Write4U]

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

But are "weighted" connections themselves not differential equations?

Method of mean weighted residuals

In applied mathematics, methods of mean weighted residuals (MWR) are methods for solving differential equations. The solutions of these differential equations are assumed to be well approximated by a finite sum of test functions {\displaystyle \phi _{i}}

. In such cases, the selected method of weighted residuals is used to find the coefficient value of each corresponding test function. The resulting coefficients are made to minimize the error between the linear combination of test functions, and actual solution, in a chosen norm.

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