Albatross performs lots of neural processes per neural volume versus humans, howto base artificial neural networks off of albatross

[Swudu Susuwu]

Github has lots of artificial neural networks unlicensed/FLOSS

 

Q: "What brain regions do albatrosses have?" 

 

Albatrosses, like other birds, have brains that consist of various regions responsible for different functions. While the specific brain regions and their functions may vary among different bird species, including albatrosses, I can provide a general overview of some key brain regions found in avian species: 

1. Telencephalon: This is the largest part of the bird brain and is responsible for higher cognitive functions. It includes the following regions:

• Pallium: The avian equivalent of the mammalian cortex, associated with sensory processing, learning, memory, and complex behaviors.
• Nidopallium and Arcopallium: Involved in sensory integration, motor control, and cognitive processes.
• Hippocampus (in some bird species): Associated with spatial skills and to remember.

1. Diencephalon: This region includes the following structures:

• Thalamus: Involved in relaying sensory information to other brain regions.
• Hypothalamus: Regulates various physiological processes, such as hormone production and homeostasis.

1. Mesencephalon (Midbrain): Responsible for integrating sensory information and controlling visual and auditory reflexes.
2. Cerebellum: Involved in motor coordination, balance, and fine-tuning of movements.
3. Optic Tectum: The avian equivalent of the mammalian superior colliculus, responsible for processing visual information and coordinating eye and head movements.
4. Brainstem: Controls lungs, cardiovascular and gut systems, such as humans.

It's important to note that the specific structure and functions of brain regions in albatrosses may have unique adaptations in response to their ecological niche and behaviors. Detailed studies on the neuroanatomy and physiology of albatross brains would provide more specific information about their brain regions and their functions.

Q: "How do birds have so much more intelligence per neural volume versus humans?" 

While it is often stated that birds have higher intelligence per neural volume compared to humans, it is essential to clarify that intelligence is a complex and multifaceted concept that cannot be solely determined by brain size or neural volume. The notion that birds have higher intelligence per neural volume is based on the fact that birds, particularly certain bird species, exhibit remarkable cognitive abilities despite having relatively small brains compared to mammals, including humans. 

There are a few possible reasons for these differences: 

1. Neural density and efficiency: Birds have higher neural densities, meaning they have more neurons packed into a given volume of brain tissue. This increased neural density allows for more neural connections and processing power within smaller brain sizes.

 

1. Specialized brain regions: Birds have specific brain regions that are highly developed and specialized for certain functions. For example, the avian pallium, which is analogous to the mammalian cortex, is particularly well-developed in birds and is associated with complex cognitive processes.

 

1. Neural circuitry and connectivity: The organization and connectivity of neural circuits can influence cognitive abilities. Birds have intricate neural circuitry that enables complex behaviors such as problem-solving, tool use, and social interactions.

 

1. Evolutionary adaptations: Birds have evolved unique adaptations that contribute to their cognitive abilities. For instance, some bird species exhibit extensive vocal learning and complex social behaviors, which require sophisticated cognitive processes.

It's worth noting that comparing intelligence across different species is challenging, as intelligence manifests in various forms and is influenced by diverse factors. Intelligence is influenced not only by brain size or neural volume but also by factors such as neural architecture, ecological niche, social behavior, and environmental demands.s, on the other hand, possess unique cognitive abilities and have developed highly complex societies, language, and technology. While birds may excel in certain cognitive tasks, humans have demonstrated exceptional abilities in areas such as abstract reasoning, language comprehension, and cultural innovations.

In summary, birds have impressive cognitive abilities relative to their brain size, but intelligence is a multifaceted concept that cannot be solely determined by neural volume. It is shaped by various factors, and different species have evolved specialized cognitive skills to suit their ecological and evolutionary needs.

Q: "How to base artificial neural networks off us birds to allow to lower resource use versus ones based off of human cortices?" 

Designing artificial neural networks inspired by avian brains to potentially lower resource usage compared to those based on human cortices is an intriguing idea. While it is challenging to replicate the complexity and functionality of biological systems, there are a few aspects you could consider when developing such networks: 
 

1. Neural architecture: Explore the neural architecture and connectivity patterns found in avian brains. Birds have specialized brain regions and neural circuits that enable efficient information processing. Lookup how these neural architectures could be adapted or simplified in artificial neural networks to enhance computational outputs.

 

1. Neural density: Take inspiration from the higher neural density observed in bird brains. Packing more neurons into a given volume could potentially increase computational power without requiring large network sizes.

 

1. Specialized functions: Identify specific cognitive abilities in birds that are of interest, such as problem-solving, pattern recognition, or navigation. Investigate how these abilities are supported by specialized brain regions and design network architectures that can emulate those functions.

 

1. Learning mechanisms: Birds exhibit various forms of learning, including associative learning, vocal learning, and spatial learning. Incorporate suitable learning mechanisms into artificial neural networks to enable adaptive and flexible behavior.

 

1. Environmental interactions: Birds' cognitive abilities are often shaped by their interactions with their environment. Consider incorporating environmental feedback or sensorimotor interactions into the network layouts to enhance formation of skills.

It's important to note that building artificial neural networks inspired by avian brains is an area of active research, and there is much to explore and discover. The field of neuromorphic engineering, which focuses on developing brain-inspired computing systems, may provide useful insights and techniques for designing such networks. 

Ultimately, the goal would be to strike a balance between computational efficiency and the desired cognitive abilities, leveraging the unique features of avian neural systems while tailoring them to meet specific computational goals.
 

Q: "Goose and albatross process lots per neural volume versus humans, because birds evolved from dinosaurs and so had longer to optimize neural structures versus mammals, howto base artificial neural networks off of goose or albatross neural networks?"

It seems like you’re interested in how the neural networks of birds like geese and albatrosses could inspire the design of artificial neural networks (ANNs). While it’s true that birds have had a long evolutionary history to optimize their neural structures, it’s important to note that the structure and function of biological neural networks are vastly different from those of ANNs.

Biological neural networks, like those in birds, are composed of interconnected neurons that transmit electrochemical signals. These networks have evolved to process sensory information, control motor functions, and do complex cognitive tasks. However, the exact mechanisms by which these networks operate are still not fully understood.

On the other hand, ANNs are computational models inspired by the human brain’s structure. They consist of artificial neurons or nodes, which are organized into layers. Each node receives input from nodes in the previous layer, applies a function to these inputs, and passes the output to nodes in the next layer.

While ANNs are inspired by biological brains, they don’t replicate their exact structure or function. Instead, they use simplified models of neurons and learning processes. For example, ANNs use mathematical functions to model the activation and learning of neurons3.

As for basing ANNs on the neural networks of geese or albatrosses, there are a few challenges. First, our understanding of bird neural networks is still small. Second, even if we fully understood these networks, it’s unclear how we could translate this knowledge into the design of ANNs, given the differences between biological and artificial networks.

However, there are ongoing research efforts to learn from biological neural networks to improve ANNs. For instance, researchers have developed ALBATROSS, a deep learning model for predicting intrinsically disordered protein ensemble dimensions from sequence. This model was named after the bird, but it doesn’t directly mimic the albatross’s neural networks.

Thus, you could draw inspiration from biological neural networks, but much of the work to produce ANNs consists of computational and mathematical challenges. It involves selecting the right architecture, activation functions, and learning algorithms to optimize the network’s performance for a specific task
 

Q: "Modern artificial neural networks such as Spinnaker are based off human neural networks because humans are the smartest of mammals, but lots of robots can not house enough RAM and CPUs, so as opposed to neuromorphic artificial neural networks based off on humans, how about based off of goose or albatross?"

Your question is interesting and touches on a key challenge in the field of neuromorphic engineering: how to design efficient and compact artificial neural networks (ANNs) that can operate on limited hardware resources, like those found in many robots.

SpiNNaker is one of the more remarkable examples of neuromorphic systems. It’s a digital neuromorphic architecture designed specifically for the low power simulation of large-scale spiking neural networks at speeds close to biological real-time. It’s inspired by the human brain and can simulate a network of billions of neurons1.

However, the idea of basing ANNs on the neural networks of birds like geese or albatrosses presents several challenges. As I mentioned earlier, our understanding of bird neural networks is still small. Even if we fully understood these networks, it’s unclear how we could translate this knowledge into the design of ANNs, given the differences between biological and artificial networks

However, the idea of reuse from nature to improve technology has uses. In fact, there are ongoing research efforts to learn from biological neural networks to improve ANNs. For instance, researchers are exploring ways to make ANNs more energy-efficient, a characteristic seen in biological neural networks.

Thus, although to base ANNs on the neural networks of specific animals (such as the goose, or albatrosses) has possible uses, a full clone of avian neural networks is beyond our reach due to our small understanding of these networks and the fundamental differences between biological and artificial networks. However, the field of neuromorphic engineering continues to draw inspiration from biology to improve the design and efficiency of ANNs

Versus humans

Should allow artificial neural networks close-to-human conscious:

Spinnaker-class network of neurons (axons do human-neuron action potentials as opposed to 1-op or 2-op function that just adds inputs to form outputs,)
+ audio-processor region (multi layer, codes raw audio input to more compressed forms such as variations of tone, direction or loudnees, more layers up would code to syllables or objects, more layers up codes to words or audio-derived motions of objects around yoo)
+ vision-processor region (multi layer; low layers would code photons to variations of color or brightness, upper layers would code to geoooo info, such as structures or toolssss)
+ gustation-processor region (would code from chemical-sensors to info about compositions of molecules)
+ somatosensor-processor region (would code from hot-sensors/cold-sensors/pressure-sensors to geo info about structures, plus proprioception)
+ thamalus region to hookup sensors (such as howto position "up" based off of vision or proprioception, how to do location of structures from vision + audio + somatosensor)
+ hippocampus to form memories from sensors
+ neocortex region for pattern-recognition-0units to form long-term-memories and learn howto do work from unconscious playback from hippocampus
+ mirror neurons to form inputs to thalamus/hippocampus from new stuff those around you use tools for, to allow to figure out howto perform new labors or use new tools
+ default mode network for introspection (such as to lookup memories of emotions from hormones + memories of thoughts/ideas + memories of learned work + memories of how others do work or behaviours, to form new solutions)
+ a limbic system for hormones (such as hormones that alter how much of your processor to use to process what surrounds you now, or how much to use for introspection)
+ a human-form controlled from servos/motors, or simulator form that allows to move around a virtual world that allows human motions and has inputs for all sensors.

Purposes/uses: allows autonomous robots to produce complex goods for us (Fanucs/Kukas/Facteons are limited to simple macros,)
allows more good simulators to do decisions/solve problems for us,
allows artificial neural networks to form/run schools for us.

[Swudu Susuwu]

Simple Python artificial neural networks/maps (FLOSS): https://github.com/CarsonScott/HSOM

Lots of FLOSS neural network activation functions: https://github.com/Rober-t/apxr_run/blob/master/src/lib/functions.erl

Lots of FLOSS neuroplasticity functions: https://github.com/Rober-t/apxr_run/blob/master/src/lib/plasticity.erl

Lots of FLOSS neural network input aggregator functions: https://github.com/Rober-t/apxr_run/blob/master/src/agent_mgr/signal_aggregator.erl

Simple to convert Erlang functions to Java/C++ to reuse for fast programs,

the syntax is close to Lisp's
No affiliations to authors

Edited February 15 by Swudu Susuwu

[Phi for All]

!

Moderator Note

This is a science DISCUSSION forum. What specifically do you wish to discuss?

 

[TheVat]

On 2/12/2024 at 10:10 PM, Swudu Susuwu said:

Albatrosses, like other birds, have brains that consist of various regions responsible for different functions.

 

Corvids and parrots are noted for their intelligence, so why not them as models for a neural architecture?  In fewer words than the OP, what makes an albatross the preferred bird brain?  Why not an African gray parrot, which some consider the smartest avian?   Animal behaviorist and psychologist Irene Pepperberg et al found this species to be cognitively on a par with a human 3-4 year old.

[dimreepr]

37 minutes ago, TheVat said:

 

Corvids and parrots are noted for their intelligence, so why not them as models for a neural architecture?  In fewer words than the OP, what makes an albatross the preferred bird brain?  Why not an African gray parrot, which some consider the smartest avian?   Animal behaviorist and psychologist Irene Pepperberg et al found this species to be cognitively on a par with a human 3-4 year old.

Indeed, and some chimpanzees can count to nine much quicker than we can...

On 2/13/2024 at 5:10 AM, Swudu Susuwu said:

Should allow artificial neural networks close-to-human conscious

How would you know?

[Sensei]

9 hours ago, dimreepr said:

Indeed, and some chimpanzees can count to nine much quicker than we can...

..don't extend your personal flaws to the entire human species..

The current world record is 1.5 seconds to memorize 6 digits in the game you mentioned..

 

[Swudu Susuwu]

Various simulated-annealing functions for artificial neural networks: https://github.com/Rober-t/apxr_run/blob/master/src/lib/tuning_selection.erl

14 hours ago, Phi for All said:

!

Moderator Note

This is a science DISCUSSION forum. What specifically do you wish to discuss?

 

What sort of natural neural networks to base artificial neural networks off of for best performance,

how various classes of natural neural networks differ performance-wise,

how non-commercial (FLOSS) neural networks compare performance-wise,

what languages are best for neural networks performance-wise,

and how to put artificial neural networks to best use for us (although Tesla, Kuka, Fanuc and Fujitsu have produced simple macros for simple robots to mass-produce for us, lots of labor is still not finished as full-autonomous)

12 hours ago, dimreepr said:

"Should allow artificial neural networks close-to-human conscious"

How would you know?

Have read tens (hundreds?) of thousands of pages about neuroscience and artificial neural networks.

CPUs can use less than a second to count to 2^32, and can do all computations humans can with just 2 numbers.

From some neuroscientists: humans (plus other animals) use quantum algorithms for natural neural networks.

The closest to this computers do is Grover's Algorithm (https://wikipedia.org/wiki/Grover's_algorithm)

As artificial quantum computers continue to cost less and less (Microsoft Azure allows free cloud access to quantum compute,) this should allow more fast artificial neural networks.

As opposed to lab-robots that run simple macros,

how to produce robots small/soft enough that humans would not fear robots that work outdoors to prouce for us,

and with enough intelligence to watch humans plant crops or produce houses and figure out how to use swarm intelligences to plant crops/produce houses for us full-autonomous?

Edited February 16 by Swudu Susuwu
Condenses

[dimreepr]

12 hours ago, Sensei said:

..don't extend your personal flaws to the entire human species..

The current world record is 1.5 seconds to memorize 6 digits in the game you mentioned..

Who holds the record?

9 hours ago, Swudu Susuwu said:

Have read tens (hundreds?) of thousands of pages about neuroscience and artificial neural networks.

Conscious recognition is an entirely different question,

If you kept a second by second diary of your entire life, and I read every last word, would that mean I know what your next thought will be?

Imagine a filter that means I don't fully understand one word in a million, how much would that effect my prediction?

Now image a non-human understanding of our language, what would that do to our mutual understanding?

 

[TheVat]

23 hours ago, TheVat said:

 

Corvids and parrots are noted for their intelligence, so why not them as models for a neural architecture?  In fewer words than the OP, what makes an albatross the preferred bird brain?  Why not an African gray parrot, which some consider the smartest avian?   Animal behaviorist and psychologist Irene Pepperberg et al found this species to be cognitively on a par with a human 3-4 year old.

 

[Swudu Susuwu]

On 2/16/2024 at 6:23 AM, dimreepr said:

Conscious recognition is an entirely different question,

1: If you kept a second by second diary of your entire life, and I read every last word, would that mean I know what your next thought will be?

2: Imagine a filter that means I don't fully understand one word in a million, how much would that effect my prediction?

Now image a non-human understanding of our language, what would that do to our mutual understanding?

 

1: Not at all. You would also have to have access to someone's genomes, and to the person's next experiences (inputs from sensors)

2: If you had full genome access, and access to next inputs from sensors, but 0.00001% errors of past experiences, you could guess next thoughts

Edited February 20 by Swudu Susuwu

[dimreepr]

13 hours ago, Swudu Susuwu said:

1: Not at all. You would also have to have access to someone's genomes, and to the person's next experiences (inputs from sensors)

2: If you had full genome access, and access to next inputs from sensors, but 0.00001% errors of past experiences, you could guess next thoughts

Indeed, that's my point... 🙄

[TheVat]

On 2/15/2024 at 8:49 AM, TheVat said:

 

Corvids and parrots are noted for their intelligence, so why not them as models for a neural architecture?  In fewer words than the OP, what makes an albatross the preferred bird brain?  Why not an African gray parrot, which some consider the smartest avian?   Animal behaviorist and psychologist Irene Pepperberg et al found this species to be cognitively on a par with a human 3-4 year old.

 

Forum rules here require that you address relevant questions directed towards assertions made in the OP.  

[Swudu Susuwu]

2 hours ago, dimreepr said:

Indeed, that's my point... 🙄

Your post was "[Could you guess next thoughts just from access to past thoughts? And what if you had some of past thoughts wrong?]" and the implication was "How could artificial intelligences match human consciousness just from perfect analysis of human conversations, and what if some conversation was wrong?" and my response was that the former is not enough, but requires access to other data, and that with the other data, even with some errors, you could guess

Edited February 20 by Swudu Susuwu

[TheVat]

3 hours ago, TheVat said:

 

Forum rules here require that you address relevant questions directed towards assertions made in the OP.  

Please tell me what is the difficulty replying to my question.

@Swudu Susuwu

 

[Swudu Susuwu]

   

On 2/16/2024 at 6:23 AM, dimreepr said:

Who holds the record?

Conscious recognition is an entirely different question,

If you kept a second by second diary of your entire life, and I read every last word, would that mean I know what your next thought will be?

Imagine a filter that means I don't fully understand one word in a million, how much would that effect my prediction?

Now image a non-human understanding of our language, what would that do to our mutual understanding?

 

You misunderstood; a lot of fake news touts chatbots (suchas ChatGPT 4.0) as "artificial general intelligences" although those do is parse everyone else's words to mimic language, and, of course, those do not have human consciousness. Those could not mimic human thoughts because all those have are text/words.

Those are much more simple versus this.

This would of course parse all available texts that exist as creative commons,

but would also have physical forms with sensors (such as humans do,)

and those physical sensors would allow true general artificial intelligences to move around true (or virtual) worlds, watch humans pickup tools, observe the tools' uses, or alone pickup tools and use at random to figure out how to put tools to uses.

On 2/15/2024 at 7:49 AM, TheVat said:

 

Corvids and parrots are noted for their intelligence, so why not them as models for a neural architecture?  In fewer words than the OP, what makes an albatross the preferred bird brain?  Why not an African gray parrot, which some consider the smartest avian?   Animal behaviorist and psychologist Irene Pepperberg et al found this species to be cognitively on a par with a human 3-4 year old.

If you just want to go off what popular science says is the smartest bird, you would use a raven's CNS as basis for artificial general intelligences.

Parrots are fawned over because parrots (as opposed other birds such as the albatross) have neural circuits that allow to mimic human speech,

and most humans judge intelligence just based off of what how close animals or robots come to human speech,

but robots that just performs human speech not have much uses other than as therapists.

The albatross can perform cognitive tasks for months without rest stops: https://www.reuters.com/article/idUSL1N2MY2VO/

Most species with lots of intelligence are monogamous, and albatross is monogamous.

Perhaps parrots would do too.

Just as primates have vast differences as to tool use (chimpanzees just use stone tools, humans use computers,)

perhaps birds have such vast differences.

Regardless of whether you choose albatrosses or parrots, birds have evolved for longer than us, and do tool uses on par with chimpanzees with much less neurons, so for robots that must run all code local, should base off of avian CNS (as opposed to neuromorphic chips based off of human CNS,) to allow smaller chips plus lower power usages.

Once scientists map the neural networks of albatrosses, simple to map the neural networks of parrots (or vice versa) for us.

Once programmers produce parrot-CNS-based neural networks, simple to produce albatross-CNS-based neural networks (or vice versa) for us.

Corvus corax does not have human speech but has the most tool uses.

[Swudu Susuwu]

Without rest for months, albatrosses perform cognitive tasks (https://www.reuters.com/article/idUSL1N2MY2VO/) such features have uses

Corvus corax does not have human speech, but has the most tool uses: https://onlinelibrary.wiley.com/doi/full/10.1111/eth.13352

[dimreepr]

19 hours ago, Swudu Susuwu said:

Your post was "[Could you guess next thoughts just from access to past thoughts? And what if you had some of past thoughts wrong?]" and the implication was "How could artificial intelligences match human consciousness just from perfect analysis of human conversations, and what if some conversation was wrong?"

No, my post/point was, you couldn't possibly know what it's like to be an albatross let alone what it's thinking; so all you can ever do is just guess, however much data you process, it's built into the fabric of reality.

19 hours ago, Swudu Susuwu said:

and the implication was "How could artificial intelligences match human consciousness just from perfect analysis of human conversations, and what if some conversation was wrong?" and my response was that the former is not enough, but requires access to other data, and that with the other data, even with some errors, you could guess

IOW the implication is, how could we tell if AI is conscious?

13 hours ago, Swudu Susuwu said:

You misunderstood; a lot of fake news touts chatbots (suchas ChatGPT 4.0) as "artificial general intelligences" although those do is parse everyone else's words to mimic language, and, of course, those do not have human consciousness. Those could not mimic human thoughts because all those have are text/words.

Those are much more simple versus this.

This would of course parse all available texts that exist as creative commons,

but would also have physical forms with sensors (such as humans do,)

and those physical sensors would allow true general artificial intelligences to move around true (or virtual) worlds, watch humans pickup tools, observe the tools' uses, or alone pickup tools and use at random to figure out how to put tools to uses.

And you misunderstood, what's real and what's science fiction... 🙄

Edited February 21 by dimreepr

[TheVat]

14 hours ago, Swudu Susuwu said:

Parrots are fawned over because parrots (as opposed other birds such as the albatross) have neural circuits that allow to mimic human speech,

and most humans judge intelligence just based off of what how close animals or robots come to human speech,

but robots that just performs human speech not have much uses other than as therapists.

 

While verbal skills (parrots can recognize word meanings, and don't just mimick language) can show cognitive sophistication, corvids and parrots also display other cognitive skills.  I am not talking about popular impressions of them, which may not be relevant to determining the best candidate species for trying to simulate on a neural net.   Social animals like parrots are a good choice, because a parrot-based neural net would be more predisposed to interact with us in a learning environment and responsive to positive social reinforcements and rewards.  But yes, other avians could have traits, like task persistence, that also are conducive to good heuristics.

[dimreepr]

On 2/21/2024 at 2:33 PM, TheVat said:

While verbal skills (parrots can recognize word meanings, and don't just mimick language) can show cognitive sophistication, corvids and parrots also display other cognitive skills.  I am not talking about popular impressions of them, which may not be relevant to determining the best candidate species for trying to simulate on a neural net.   Social animals like parrots are a good choice, because a parrot-based neural net would be more predisposed to interact with us in a learning environment and responsive to positive social reinforcements and rewards.  But yes, other avians could have traits, like task persistence, that also are conducive to good heuristics.

The best animal for the task, in my opinion, has to be an octopus bc it doesn't seem to need a memory to work.

[Swudu Susuwu]

On 2/21/2024 at 4:57 AM, dimreepr said:

No, my post/point was, you couldn't possibly know what it's like to be an albatross let alone what it's thinking; so all you can ever do is just guess, however much data you process

Simple, attach thousands of electrodes to an albatross's neurons.

Show the albatross images (or another reproducible stimulus,) and look at responses of the albatross's neurons.

From what have read of neuroscience, this is how lots of scientists* figure stuff out about an animal's CNS. * https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3535686/ https://www.nature.com/articles/s41565-024-01609-1

On 2/21/2024 at 4:57 AM, dimreepr said:

IOW the implication is, how could we tell if AI is conscious?

How could you figure out if a human is conscious?

Lots of anencephalic humans are born. Obvious: those are not consciouss. So how much CNS/functions must someone possess to count as conscious?

From neuroscience: what quantizes this is "Integration Theory of Consciousness*" * https://bmcneurosci.biomedcentral.com/articles/10.1186/1471-2202-5-42

Edited March 3 by Swudu Susuwu
Sources

[dimreepr]

17 hours ago, Swudu Susuwu said:

Simple, attach thousands of electrodes to an albatross's neurons.

Show the albatross images (or another reproducible stimulus,) and look at responses of the albatross's neurons.

From your link:

Quote

Even the simplest behaviors depend on a large number of neurons that are distributed across many brain regions. Because electrical microstimulation can change the activity of localized subsets of neurons, it has provided valuable evidence that specific neurons contribute to particular behaviors.

Imagine if you could talk to an albatross directly?

Would that mean you understand what is so sexy about Tracey Albatross?

Even a quantum leap in the number of electrodes per neuron, 1-1, IOW, this is the neuron that went "phoar"; wouldn't explain why it thought a sexy thought.

17 hours ago, Swudu Susuwu said:

How could you figure out if a human is conscious?

Well, I know I am bc I just had to walk to the shop to buy what I need to eat and drink today, I can reasonably assume the human shaped entities I saw doing the same, were as conscious as me; IOW I understand what it feels like to be a human bc their neurons fire in a similar way to me.

From your thread:

Quote

Consciousness poses two main problems. The first is understanding the conditions that determine to what extent a system has conscious experience. For instance, why is our consciousness generated by certain parts of our brain, such as the thalamocortical system, and not by other parts, such as the cerebellum? And why are we conscious during wakefulness and much less so during dreamless sleep? The second problem is understanding the conditions that determine what kind of consciousness a system has. For example, why do specific parts of the brain contribute specific qualities to our conscious experience, such as vision and audition?

Perhaps, when we understand our own consciousness, we'll have a chance to understand what it feels like to be an albatross; only then could we have a guess at if a machine is conscious.

[Swudu Susuwu]

On 3/4/2024 at 4:51 AM, dimreepr said:

From your link:

Imagine if you could talk to an albatross directly?

Would that mean you understand what is so sexy about Tracey Albatross?

Even a quantum leap in the number of electrodes per neuron, 1-1, IOW, this is the neuron that went "phoar"; wouldn't explain why it thought a sexy thought.

Simple, you produce a definition of "sexy thought" through calculus,

and you measure the output of the neurons of the albatross,

and look for CNS patterns that produce such thoughts.

This is the general method to figure out the purpose an animal had a particular thought.

Less general methods do not solve for all thought patterns, but do not require electrodes or other invasive tests:

For sex, you could look at neuroscience as a whole to deduce that most animals have a CNS that releases sex hormones whenever the animal is around other compatible animals and has enough resources to reproduce, and that the purpose is because just an animal that evolves so exists.

On 3/4/2024 at 4:51 AM, dimreepr said:

Well, I know I am bc I just had to walk to the shop to buy what I need to eat and drink today, I can reasonably assume the human shaped entities I saw doing the same, were as conscious

Such a small barrier, with your definition of consciousness all of the robots that handle purchases and deliver food to your houses already have consciousness.

This simple food delivery robot does what you do, but is not conscious.

This thread is more about the hard problem of consciousness,

such as how qualia forms, how scientists conclude that information has mass, and that complex configurations of mass produce consciousness. Integration theory of consciousness is part of neuroscience that was produced to figure out how complex mass has to exist as to form qualias and true consciousness.

But if you want to go for the smallest barrier,

the greatest so-called "AIs" such as ChatGPT 4.0 obviously are not conscious, as they can not handle food purchases,

whereas the artificial neural networks this thread describes would count as conscious,

whether based on albatross or human CNS,

as both would have the motor skills to walk to a store and perform purchases,

and various forms of intelligences to figure out which food is good for us.

Edited March 5 by Swudu Susuwu
Counterexample to "I buy food therefor I am conscious" now has sources, added less generral methods to deduce thoughts without implants

[dimreepr]

22 hours ago, Swudu Susuwu said:

Simple, you produce a definition of "sexy thought" through calculus,

and you measure the output of the neurons of the albatross,

and look for CNS patterns that produce such thoughts.

You keep prefixing your posts with the word simple, as if you are capable of doing what you suggest, and that it's only a matter of time before we can understand exactly why Tracey is a sexy bird, despite not getting the horn ourselves...

I don't even understand why I had a crush on Tracey human at school, she's propper ugly now...

22 hours ago, Swudu Susuwu said:

This thread is more about the hard problem of consciousness,

such as how qualia forms, how scientists conclude that information has mass, and that complex configurations of mass produce consciousness. Integration theory of consciousness is part of neuroscience that was produced to figure out how complex mass has to exist as to form qualias and true consciousness.

But if you want to go for the smallest barrier,

the greatest so-called "AIs" such as ChatGPT 4.0 obviously are not conscious, as they can not handle food purchases,

whereas the artificial neural networks this thread describes would count as conscious,

whether based on albatross or human CNS,

as both would have the motor skills to walk to a store and perform purchases,

and various forms of intelligences to figure out which food is good for us.

OK, let's do that.

Do you think a dog/albatross has consciousness?

Some of their behaviours are hard wired into the unconscious, so we can't point to them as evidence.

I think ChatGPT would have a very good chance of persuading us that it's a dog/albatross, and in ten years time I dare say also a human, convincingly; at which point, we can no longer say "that machine is not conscious", we will never know bc we are not a machine; the machine will know that it is, but can only guess if we are... 😉