• Moliere
    4.6k
    No, I did not read your SEP article yet. I will, a bit later.Carlo Roosen

    Cool!

    Let me know what you think after reading it.

    I'm here as a friend to odd ducks, and my posts are meant to help.
  • Carlo Roosen
    243
    To be more precise, before I came here I tried to engage a group of programmers. I wrote my ideas in a kind of booklet, that I put on my website, both as a pdf and as html.

    This attempt failed because programmers are too busy with all the new developments, mine were too far-fetched and philosophical for them. So I decided that I wanted to join this forum.
  • Moliere
    4.6k
    Sounds like my life!

    I want you here. New minds and new ideas are good.

    We're just trying to teach you how to do it, is all. As philosophers do.
  • Carlo Roosen
    243
    Sorry but I cannot feel much sympathy while you just accused me of promoting my website here. That post was edited with no good reason and that guy who did it should not be a moderator. What he said is unacceptable.
  • Carlo Roosen
    243
    Except for my first post, all texts were original. The first was accepted by the admin himself.
  • Carlo Roosen
    243
    This is unacceptable
    you've shown no evidence that I'm aware of that you know anything interesting about anything at all, including AI. If you provide that evidence and don't engage in any self-promotion whatsoever from now on, you can stay. Otherwise, you may not be contributing to the site and may not be allowed to stay.Baden
  • Carlo Roosen
    243
    No worries, I am good. But things must be named.
  • Outlander
    2.1k


    Ok, ok, life is unacceptable at times. Let us move on please.

    (in reply to your reply to my question)
    That's a lot to process. In fact, I'm going to have to read that twice. In the mean time, I have to ask, are you really just trying to create a computerized model of a human brain? Operating identically as our own from infancy (blank upon launch, perhaps, minus core functions required to "learn") to masterful adult? It sure sounds like it. :grin:
  • Moliere
    4.6k

    I'm wrong in saying you're here to promote your website, given what you've done thus far. You convinced me here:

    Is it ok if I refer to "Bubblespeak" in the future? I don't mind.
    I can unpublish my website, I don't mind.

    But people are asking for more information about my project. Even in this thread, unenlightened was asking more. How should I handle that? Earlier I said, look at my profile, you'll find a link. Mentioning that was allowed, according to jamal. I said a few times Google "Babelspeak", maybe that I shouldn't do?

    I am reasonable. But please give me a workable solution.
    Carlo Roosen

    You came up with reasonable solutions and followed through on them. That demonstrates willingness to cooperate, which is good!

    As I said, I'm a friend to odd ducks. I'm typing these things to you in the hopes that you can get along with the bunch.

    We're all odd ducks, to be frank. And some of your thoughts aren't as original as you think.

    But they are philosophical, which is good!
  • Carlo Roosen
    243
    I'm good. I just want to avoid having to go through this for the 4th time. I hope you have some common thread to discuss these things.
  • Carlo Roosen
    243
    I'm typing these things to you in the hopes that you can get along with the bunch.Moliere

    So far I have lots of fun with everybody except the moderators ;). No worries, I'm fine.

    I have one idea, maybe do not let new members publish on the home page. I didn't even know that some topics were not on the home page.
  • 180 Proof
    15.3k
    People on the forum said it is not allowed to talk about fundamental reality...Carlo Roosen
    That's news to me. There are at leaat hundreds of threads wherein "fundamental reality" (i.e. ontology, metaphysics) is discussed. I even refer to the topic on my profile page. Use the site's search function to find those discussions and (maybe) contribute.
  • T Clark
    13.8k
    The solution is we delete your posts and ban you.Baden

    Whatever the merits of your position, which I have doubts about, it’s not appropriate for you to take them up in public. You should deal with them in PMs. Isn’t that the normal approach with moderation?
  • Carlo Roosen
    243
    After a good night sleep I finally understand what they meant. I had my personal notes on a public website, to be able to share them with a few friends. I referred to these notes as "a booklet". The domain name of that website matched the name of the language I was using in my ideas (from now on bubblespeak here). Because I was talking on the forum about the same topics as my personal notes it was perceived as self promotion. But I had no links, all text I wrote here were original. All communications here I was polite. Nobody ever explained to me what I did wrong. Instead I was basically called a know-nothing by mr Baden, and I had to prove that I was an AI expert. And in public, yes. I still find that unacceptable. If you can do anything to correct these posts, I would be very grateful.
  • punos
    561
    The solution I have in mind, and one that I am currently writing at "tic tac toe" level, is that halfway the neural net I will have an abstraction layer with a smaller number of nodes. Then there is a decision algorithm that is fully governed by other neural nets that decides whether the information continues the normal route or goes to another module.Carlo Roosen

    Before using a bottleneck abstraction layer, you should probably develop some kind of function or algorithm that determines the maximum number of features in a piece of input information in order to avoid incurring some degree of information loss. This "max_features" function could set the number of nodes in the abstraction layer. If there are too few nodes at this layer, the network loses the ability to consider or transfer to other nodes or modules potentially essential features. The decision algorithm might not have enough feature data to make an optimal decision and becomes prone to underfitting. Too many nodes will make it too computationally inefficient and could potentially cause overfitting as well.

    I wonder if information flowing through a divergent neural network with more nodes per consecutive layer can extract the maximum number of features. Every layer would contain 1 or 2 more nodes than the prior one. As the information runs through this expanding network, the information is stretched, so to speak, separating entangled features. The process reminds me of what happens in a light prism. As the light passes through the prism, the light detangles and spreads apart the features of the light (colors). Metaphorically, if you took one of these colors and put it through another prism and no more colors or features are separated, then it's a fundamental feature or color. The expanding network would geometrically resemble a prism as well with its triangular topology or shape.

    I don't know, perhaps you've already thought of this.
  • Carlo Roosen
    243
    I have another suggestion. Good thinking! I'll come back to it.
12Next
bold
italic
underline
strike
code
quote
ulist
image
url
mention
reveal
youtube
tweet
Add a Comment

Welcome to The Philosophy Forum!

Get involved in philosophical discussions about knowledge, truth, language, consciousness, science, politics, religion, logic and mathematics, art, history, and lots more. No ads, no clutter, and very little agreement — just fascinating conversations.