The problem is that there will always be holes in philosophical ideas, some more than others. — Beverley

I think some people feel they can avoid such pitfalls if their logic is stringent enough (without being aware that extreme-logicism can itself constitute one of the "holes" of which you speak).

That is precisely where I was going. You took the words right out of my mouth ;) — Beverley

Yes, I kind of figured. It was only a matter of time.

Moral Education
by Émile Durkheim

Ontology if it gives as the list of basic categories is not a result of metaphysics too. — Johnnie

Ontology is the heart of metaphysics. And this is its traditional accepted definition, the nature of being, contrary to your assertion.

It is really difficult to have a productive conversation if you cannot contend with my responses. I am not sure how to proceed from here, but, then again, it seems like you aren't interested in having any conversation about it (and if that is the case, then we can end our conversation here: no problem). — Bob Ross

Ok Bob. How does the perfect nuclear weapon fit into your schema? Since human beings are arguably impairing the perfect balance of our eco-sphere, utilizing the perfect nuclear weapon to erase humanity would seem to be an ideal example of goodness.

What is Pattern Recognition?
Pattern recognition is a process of finding regularities and similarities in data using machine learning data. Now, these similarities can be found based on statistical analysis, historical data, or the already gained knowledge by the machine itself.

A pattern is a regularity in the world or in abstract notions. If we discuss sports, a description of a type would be a pattern. If a person keeps watching videos related to cricket, YouTube wouldn’t recommend them chess tutorials videos.


Examples: Speech recognition, speaker identification, multimedia document recognition (MDR), automatic medical diagnosis.

Before searching for a pattern there are some certain steps and the first one is to collect the data from the real world. The collected data needs to be filtered and pre-processed so that its system can extract the features from the data. Then based on the type of the data system will choose the appropriate algorithm among Classification, Regression, and Regression to recognize the pattern.

https://www.analyticsvidhya.com/blog/2020/12/an-overview-of-neural-approach-on-pattern-recognition/


Filtering and pre-processing means identifying exactly how the training data fits the data-categories for which the neural network is to be trained.

I'll ask it one more time: How do you think the computer system gains the initial information that a certain picture represents a certain thing? It does not possess innate knowledge. It only knows what it has been told specifically. I know how it's done, its done by training up the system using a training dataset in which the data is identified. The classic example is the mine-rock discriminator. Sonar profiles of "known mines" are fed into the system. Along with sonar profiles of "known rocks". These are pre-categorized by the developers. After that, the neural network is fed novel data, which it then attempts to categorize. If it is wrong, the error is "back-propagated" across the network to correct the "weights" of the hidden-architecture neurons. And this back-propagation is ALSO a manual function, since the computer does not know that it is making an error.

Training an Artificial Neural Network.In the training phase, the correct class for each record is known (this is termed supervised training), and the output nodes can therefore be assigned

Yes, supplied by external sources, not by the researchers. There, the fourth time. — Lionino

The people developing the neural net (aka the developers) are the external sources. Who else do you think, the neural-net police? The bureau of neural net standards? Jeez. Here's wikipedia on Labeled_data

Labeled data is a group of samples that have been tagged with one or more labels. Labeling typically takes a set of unlabeled data and augments each piece of it with informative tags. For example, a data label might indicate whether a photo contains a horse or a cow, which words were uttered in an audio recording, what type of action is being performed in a video, what the topic of a news article is, what the overall sentiment of a tweet is, or whether a dot in an X-ray is a tumor.
Labels can be obtained by asking humans to make judgments about a given piece of unlabeled data. Labeled data is significantly more expensive to obtain than the raw unlabeled data.


Anyway, to the OP in general, I think I've conclusively and exhaustively demonstrated my point. And illustrated the very real dangers of a naive techno-optimism. If anything, we should be constantly tempering ourselves with a healthy and ongoing attitude of informed techno-skepticism.

One final cautionary. I worked as a technical expert in the health-care industry until this year, so I've seen a couple of these studies circulated on "baked-in" AI bias.

For example, if historical patient visits are going to be used as the data source, an analysis to understand if there are any pre-existing biases will help to avoid baking them into the system,

The article you linked sets out to show that humans may inherit the biased information given to them by an AI (duh), not that AI inherits human bias. :meh: — Lionino

Which bias originally derived from the biased input data, as is in the article.

Like I said, it's a fact. Do some reading. "Training up" a neural net. Categorization is supplied, it's not intrinsic to the nature of a picture Copernicus.

It’s not necessary that a metaphysical outlook be identically shared among members of a community. Each of those diverse humans you have encountered has an interpretive system for construing events which is partially unique to themselves. — Joshs

Indeed. And there are limits both to the extent that it is actually "shared" (different degrees of understanding of the same thing (ability and specialization) and different aspects of the same thing (complexity) being some limitations. And there are similar limits constraining the extent that an individual can diverge, social pressures and norms, as well as the inherent need for one's core metaphysic to meet whatever constitutes its conditions of "adequacy" to be one's core metaphysic.

We should never have invented agriculture. — bert1

The Dawn of Everything evaluates this position, and also explores the unique power of the indigenous world view through some historical analysis informed by native sources and details.

In any case, I still have not seen any proof that programmers are categorising their own data by hand. — Lionino

I'm sorry, perhaps you just do not understand the way neural networks function. Do you think that the data categorizes itself? This isn't a subject of debate, it is how they work. I've provided excellent, on-point information. Beyond that, I suggest studying the "training up phase" of neural network design:

Usually, an artificial neural network’s initial training involvesbeing fed large amounts of data. In its most basic form, this training provides input and tells the network what the desired output should be. For instance, if we wanted to build a network that identifies bird species, the initial training could be a series of pictures, including birds, animals that aren’t birds, planes, and flying objects.

Each input would be accompanied by a matching identification such as the bird’s name or “not bird” or “not animal” information. The answers should allow the model to adjust its internal weightings to learn how to get the bird species right as accurately as possible.

https://blog.invgate.com/what-is-neural-network

I've been studying neural networks since the 1990's, long before they were popular, or even commonly known.

There is no "AI" my friend. All there is is "pattern-matching" software, that has been trained based on pre-selected data, which selection has been made by biased human beings. The "Big-AI" players are all commercial enterprises. Do you not think that there are massive agendas (aka biases) skewing that data? Come on.

the AI system trained with such historical data will simply inherit this bias

This study shows that a bias (error) originally inherited by the AI from its source data in turn is inherited as a habit by students who learned a diagnostic skill from the AI.

So technology is actually amplifying an error, and the confidence which people have in it only exacerbates the extent to which this is a problem. Which is what I originally suggested.

I hope that I am slightly less ignorant than two decades ago, If that is true, it is because I feel and do things differently. — Paine

This is how I feel.

↪Pantagruel "Beliefs" such as? Also, please clarify what you mean by "embracing them fully". — 180 Proof

Like stoicism. You can read all the stoicism you want. But there is a difference between reading it, and believing it to the extent that you actively, even transformatively embrace it. Or perhaps something more esoteric. But along those lines.

Where have I claimed there are no possible further dimensions to human understanding? — Janus

I wasn't implying you had said, it was just an ongoing observation.

For certain things types of things, we can only really ever know the results of beliefs we are willing to test by embracing them fully.

Second Stage Lensmen (Lensman #5)
by E.E. "Doc" Smith

Here's an example.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3281765#:~:text=First%2C%20AIs%20could%20display%20a,the%20doubt%E2%80%9D%20in%20uncertain%20situations.

However, re. your argument, there is absolutely no question that people are categorizing things like this. If you are talking purely material states, ok sure, you can accurately and comprehensively identify a material configuration, circles, magnetic profiles of ships, you name it. But anything that involves a human evaluation for which there can be a range of interpretations is subject to this bias. It's absolutely inherent in the nature of neural networks.

https://theconversation.com/emotion-reading-tech-fails-the-racial-bias-test-108404

https://www.nytimes.com/2016/06/26/opinion/sunday/artificial-intelligences-white-guy-problem.html

The dataset can never be more neutral than what is being evaluated. People are interested in categorizing what people do in order to get them to do certain things. It's probably the most subjectively-laden data-interpretation that there is (even when it comes to identifying what constitutes data). Ask ChatGPT if its answers could be subject to unknown selection biases its developers may have passed on to it accidentally through data-categorization.

edit. I just did it. Here's what it told me.

So if that's the case, then couldn't your ability to identify something be subject to unknown selection biases your developers may have passed on to you accidentally through the initial data selection and identification?

ChatGPT
Yes, you've touched upon a crucial aspect of machine learning systems, including neural networks: the potential for biases to be inadvertently introduced through the training data and labeling process. These biases, which may be present in the data collected or the decisions made during the training phase, can influence the behavior and performance of the model, potentially leading to unintended consequences. Here are some key points to consider:

Data Selection Bias: The selection of training data plays a significant role in shaping the behavior of a machine learning model. If the training dataset is not representative of the target population or contains inherent biases, the model may learn to replicate and amplify these biases in its predictions. For example, if a facial recognition system is trained predominantly on images of individuals from certain demographic groups, it may perform poorly on individuals from underrepresented groups.

Labeling Bias: The process of labeling training data can also introduce biases if the criteria for assigning labels are subjective or influenced by human judgment. Annotators may inadvertently introduce their own biases or assumptions when labeling data, leading to inaccuracies or distortions in the training dataset. For instance, if annotators have preconceived notions about certain concepts or categories, they may label data in a way that reflects these biases.

Algorithmic Bias: Even if the training data is unbiased, the algorithms used to train machine learning models may exhibit bias due to the optimization process or inherent limitations of the algorithm. For example, certain types of neural network architectures may be more prone to amplifying biases present in the data, or the choice of loss function used during training may inadvertently prioritize certain types of errors over others.

Mitigation Strategies: To address these concerns, developers and researchers employ various strategies to identify, mitigate, and address biases in machine learning systems. These may include carefully curating diverse and representative training datasets, implementing fairness-aware algorithms that explicitly account for biases, and conducting rigorous evaluation and testing to assess the performance of the model across different demographic groups and use cases.

Overall, while machine learning systems offer powerful tools for pattern recognition and decision-making, it's important to recognize and mitigate the potential for biases to influence their behavior. By taking proactive steps to address biases in the data, algorithms, and decision-making processes, developers can help ensure that machine learning systems are fair, transparent, and accountable.

I think when you pursue the esoteric you are taking a risk. You risk being seen as an outsider by a certain subset of exoterically-content people. You risk vital time and energy that you are investing in a seemingly fruitless enterprise. Perhaps the greatest risk of all is the risk of belief. If an esoteric teaching is to have value I would assume it would involve changing the way in which one lives, and that can only take place through a genuine insight born of committed belief. Assuming the esoteric knowledge to be of actual value.

Did they? AI models typically use thousands or millions of datapoints for their algorithm. Did the programmers categorise all of them? — Lionino

Absolutely. A computer doesn't "decide" the meaning of a facial configuration. The only way a computer knows what is "happy" is if someone feeds it in say one-hundred pictures of "happy" faces and tags each one as "happy". Then you can feed it in millions more pictures, if you like, and refine it's capabilities. But if that is to work (backpropagation of error) then there has to be some standard against which to "correct" the input. i.e. someone still has to correctly identify when the computer makes a mistake in categorizing a happy face, and propagate that error back through the neural network architecture.

I understand this is simply an illustrative example for your sensible point, but yet on this particular reason programmer bias is likely not the reason. If the AI detects them as angry, there must a reason why, surely the programmer did not hard code "if race == black{emotion=angry}". It could be that the black people from the sample indeed have angrier faces than other races for whatever reason, but it could also be that the data that was fed to the AI has angry people as mostly black — though a Google query "angry person" shows almost only whites. — Lionino

Neural networks work through pattern identification basically. However there is always a known input, it is the responses to known inputs against which the backpropagation of error corrects. In the example I gave, the original dataset of training images had to be identified each as representing "joy", "surprise", "anger," etc. And the categorizations of interpretations of the images of black people were found to be reflective of the selection bias of the developers (who did the categorizing). And all AI systems are prone to the embedding of such prejudices. It is inherent in their being designed to certain purposes that specific types of preferences dominate (aka. biases).

I think that in the sense that practical logic is the foundation of more complex forms of reasoning, including mathematics, you could argue that numbers begin with self-identity, which is unity, or one.

At what point does an advance become inherently good? For example, It has been shown that AI systems propagate the inherent biases of the developers who select the data used to train the neural networks. Most recently the example of the AI system designed to evaluate human emotion from faces that identified an inordinate number of black people as angry. So, for all intents and purposes, AI systems are mechanisms for perpetuating biases in the guise of science. How is that inherently good?

The proliferation of digital technologies has fundamentally altered the way that people assimilate and utilize data. There is an apparent correlation between the rise of technology and the decline of IQ. Digital communication is quickly replacing personal communication. But digital communication is a poor substitute. People act differently behind a veil of full or partial anonymity. They are more aggressive, more critical. I'm trained as a coder, worked twenty-five years as a systems administrator and a systems engineer. I use my phone less than five minutes a week and plan to keep it that way.

No, technology is not inherently good. Nothing is inherently good. The use that people make of something, that is what is good or bad.

I think it has to be acknowledged that esoteric ideas just as religious faith and adherence to metaphysical views can change one's worldview and consequently experience. — Janus

Yes. Even if it were only this, that would be enough. But the fact is, if you radically alter the nature of your being, the way that you live, you can begin to see patterns of feedback from people, society, and the universe, that you did not before. To that extent, it can be 'scientific'. As I have said and will continue to say, the human mind is very limited, so to presuppose that there are not further dimensions to understanding is just poor reasoning. Evolution documents their emergence.

I play devil's advocate for the esoteric because I believe that the goal of seeking to expand the understanding beyond the mundane can be a valid one. I don't seek to defend all esoterica, but certainly the goal and motivation of studying them. I wouldn't want to try to persuade someone who hadn't arrived at the conclusion based on his own experiences. Not everyone is suited to every kind of activity. However I do have beliefs concerning the nature of consciousness qua intersubjective and collective, for example, and concerning the relationship between pure mind and pure matter, including the nature of each, that tend to overflow the limitations of current scientific understanding, which might fit in the esoteric category.

With all due respect: prove it. Respond to the historical examples I just gave. — Bob Ross

With all due respect, I wouldn't know what to prove. What are you trying to do, establish an objective foundation for morality in order to eventually link it back to human actions? The moral law within is a moral law because it is prescriptive. Do your thing. It makes no sense to me, I am willing to leave it at that. As far as proving it, I did repeatedly. So clearly you and I are not on the same page.

Your definitions aren't bad as a general, practical notion; but will never stand up to scrutinous refinement in ethics. — Bob Ross

I've studied ethics extensively and I think you are well off-base. I'll leave you to your musings.

Cool. I like to read contrasting theories, promotes a healthy mental dialectical balance. :cool:

Morality is not conventionally nor historically only about human actions. The vast majority of human beings have been, historically speaking, moral realists; and they believed in The Good (i.e., an objective goodness) which is independent of any stance a subject may have on the matter. To think that these moral facts are only about human actions is an incredibly narrow interpretation of morality. — Bob Ross

It isn't a "narrow" view of morality Bob, it is the definition of morality.

"a particular system of values and principles of conduct, especially one held by a specified person or society."

"the extent to which an action is right or wrong"

"certain codes of conduct put forward by a society or a group (such as a religion), or accepted by an individual for her own behavior, or"

"a code of conduct that, given specified conditions, would be put forward by all rational people"

"a set of personal or social standards for good or bad behaviour and character"

It strains credulity that you would argue this. Whatever it is you're trying to get at, it isn't morality. And trying to categorize it as morality only confuses your presentation.

If the standard of conduct whereby actions are evaluated is not morality, then what is it that you call the standard of conduct whereby actions are evaluated?

I really admire his process philosophy, I think it meshes perfectly with systems philosophy. But PR has been in my library for over a decade, I got really intimidated when I first tried it and haven't touched it since. I think I'll put it on the list for later this year though. Tough read!

Still working through this. A Doozy if ever there was one. — AmadeusD

Are you enjoying?

I think I agree, but I would add that it is not the expression of anger which is the biggest problem today in our polarized world, but the failure to see the world from the perspective of others such that what appears as malevant intent can be seen instead as the other’s best effort to live ethically based on their vantage. Anger is blame, and blame impugns intent, delegitimizing the other’s motives. Whether we express our anger or not , as long as we cling to blame, we delegitimize the other, as seen in today’s political discourse. — Joshs

I think I agree too.

The litany of aggravating events that pile up over the course of the day are not stored in some internal ‘anger pot’ as the accumulation of a random collection of negative energy, — Joshs

Are they not indeed? People who are the subject of systemic environmental and social disadvantage might disagree.

Anger is a manifestation of our own failure to find a more productive expression, one which solves the problem. The problem is, the proximate cause is not always the only - or the real - problem.

So the way I would construe anger is as a rapid , multi-step construal of a situation that begins with loss and disappoint, and is immediately followed by assessment of blame. — Joshs

I wake up late and have to skip my breakfast and coffee. So I am edgy and aggravated. While running for my bus, someone beats me to it and takes the last possible free spot, so I have to wait for the next one. I enter the morning meeting late only to find that my boss has given a choice assignment to someone else. I am angry at my boss, and at the person given the assignment.

The point is, you can't reduce anger to a logically valid behaviouristic framework. Human interactions are "overdetermined" to use psychiatric jargon. Anger perhaps most of all. At the end of the day, as I said, it isn't wrong or even mysterious that we become angry, but it is usually unproductive to allow anger to determine our responses.

'Philosophies of life' usually propose exercises (e.g. meditating, caretaking, suspending judgment, flowing, being indifferent to whatever cannot be controlled, etc) for cultivating habits of equanimity, which IMO grounds courage (i.e. the skill-set for adaptively, or proactively, using – thriving from – loss, failure or uncertainty). — 180 Proof

:up:

Stoicism should be taught to elementary school students.

As said, it is really just an example of the problem with "reacting" versus "acting." Anger can be one factor in your response, as you say Jack, if it is motivated by injustice, but it should always be tempered with other influences, reason, compassion, sociability. It is a lesson that took me decades to learn intellectually, and a few years more to adopt habitually.

But this description seems to separate anger from the perceived meaning of a situation. In your paragraph above, what would happen if we removed the word anger and attributed legitimacy, strength , courage and motivation to the nature of the situation as it is construed , rather than to some separate device we call anger adding these qualities as some special spice? It is the world that is angering, not our physiology. — Joshs

One can become angry, yet not allow anger to dictate or motivate one's responses. Becoming angry does not entail displaying anger. I guess anger could be viewed as a "motivational challenge".

Anger can often be frustration at our own ability to come up with something better than anger.

Bitch — Joshs

:kiss:

Anger can be legitimate and yet still unhelpful. It can be a source of strength, courage, and motivation, but only if effectively sublimated.

Discussions on the philosophy forum often deteriorate into angry exchanges. In those cases, anger is counter-productive to philosophy.

In the real life conundrums of life, including the nature of anger, the differences in the emotions and ideas of anger may be profound — Jack Cummins

It just seems all extremely general and of almost unlimited scope. You may become angry because I argued for the legitimation of the concept of pathology, a term which you associate with a specific form of prejudice but which has a neutral-functional definition. In that case, is your anger with me, with pathology, or with something else? People can and do become angry for no apparent reason, because they are under various forms of stress. I'd suggest trying to focus the discussion more.

My distinction between anger and hatred comes from Sartre's Transcendence of the Ego.

edit: Actually I do have one additional general concept to add to the burgeoning mass of generalities. I think that "frustration" may be a not insignificant factor in the dynamics of anger and hatred.

You may be right about common sense of ideas about what constitutes anger. However, pathology in itself is a construct. Here, I am not trying to suggest a necessary going 'beyond good and evil', but more a way in which ideas taken to an extreme can mask so much. For example, in war the idea of an enemy, may evoke so much about ideas of justice, or injustice. A person who Is different, or has different beliefs may be perceived as an oppositional force.

This may be where values come into play, and insistence on one's own set may even lead to a self-righteous sense of anger, to the extent of an argument for the 'common good'. This makes ideas of anger, justice and injustice a controversial area of social ethics. — Jack Cummins

Hmm. I don't think pathology is entirely a construct Jack. Organic systems have a baseline state of operation known as health. Broadly speaking, this can be extended to the psyche. If any function within a system begins to operate in a way that impairs the function of other functions or of the system as a whole, then that is pathological. However I do know what you mean and agree that it can become or be used as a construct that can itself be harmful.

It sounds to me like you want to focus on "justified" anger, anger towards socially endemic problems. Presumably the role of anger is to motivate action?

I don't know what you mean by "objective perspective", perspective is something subjective. — Lionino

Well, a perspective can be objective. It can also take an object (intentionality) which is what I meant. An object of a perspective can be material or it can be mental.