Recent Posts

Pages: [1] 2 3 ... 10
Welcome to AI Dreams forum. / Re: Linking to AiDreams.
« Last post by DemonRaven on Today at 01:30:03 am »
That is really cool. You have really done a lot of good work.
Welcome to AI Dreams forum. / Re: Linking to AiDreams.
« Last post by on Today at 12:03:40 am »
Thanks Raven!

Here's what I've been working on...

General Chat / Re: We can't prove or disprove some sentences
« Last post by ivan.moony on September 24, 2018, 06:17:15 pm »
About defining truthfulness

While designing a logic language, I encountered this problem in defining how true formulas should look like. The problem was in that when we define a general formula `GF` such that `True <-> GF`, the whole system always collapses to `True`, and then back to the whole `GF` when we instantiate either of `GF` elements. Because hard-coding any constants was not a desired option, a compromise solution had to be found. Such a compromise would let us use the notion of truth without violating Tarski's results. It happens that such a compromise exist. We may define an analogue to a general truth at the root of the whole system by a plain consequence like `Top -> U`, where `U` is a growing Universe of expressions that are true, while the same Universe is considered as an underlying theory we want to express in our logic language. Specific fragments of this Universe still have a chance to recursively loop back to `Top` symbol without making the system collapse. In a free interpretation, `Top` symbol represents only a given subset of all possible true formulas, which is why its name is distinct from `True`. Of course, the `Top` symbol is not globally restricted, yet it is as extensible as the universe `U` is.
AI Programming / Re: Does AGI have to be a network
« Last post by WriterOfMinds on September 24, 2018, 04:05:46 pm »
You mention specialized, "hardcoded" algorithms. Being frozen, don't they limit the potential evolution of the system?

When I said specialized, I didn't mean frozen.  Such algorithms can make provision for learning and self-adjustment, though it is likely that they would not be *completely* flexible -- there would be some fixed core.  In the limiting case of a fully developed AGI that has equivalent skill to a human programmer, it would be capable of changing and re-optimizing its own algorithms to any degree desired.

It may be worth mentioning that the "G" in AGI is a relative term.  Human intelligence is the most generalized biological intelligence we know of, but even it should not be regarded as fully general.  For instance, the sensory processing abilities of our brains may be adapted to the senses we have.  Different brain regions handle different senses, suggesting some underlying structural optimization.  If you hooked our brains up to something exotic (like the electroreception organs of a shark), it is unclear how well they'd do at handling that information.

There's probably a tradeoff to be made between complete plasticity/generality and effectiveness at any given task.
Robotics News / Recognizing the partially seen
« Last post by Tyler on September 24, 2018, 12:01:51 pm »
Recognizing the partially seen
20 September 2018, 5:40 pm

When we open our eyes in the morning and take in that first scene of the day, we don’t give much thought to the fact that our brain is processing the objects within our field of view with great efficiency and that it is compensating for a lack of information about our surroundings — all in order to allow us to go about our daily functions. The glass of water you left on the nightstand when preparing for bed is now partially blocked from your line of sight by your alarm clock, yet you know that it is a glass.

This seemingly simple ability for humans to recognize partially occluded objects — defined in this situation as the effect of one object in a 3-D space blocking another object from view — has been a complicated problem for the computer vision community. Martin Schrimpf, a graduate student in the DiCarlo lab in the Department of Brain and Cognitive Sciences at MIT, explains that machines have become increasingly adept at recognizing whole items quickly and confidently, but when something covers part of that item from view, this task becomes increasingly difficult for the models to accurately recognize the article.

“For models from computer vision to function in everyday life, they need to be able to digest occluded objects just as well as whole ones — after all, when you look around, most objects are partially hidden behind another object,” says Schrimpf, co-author of a paper on the subject that was recently published in the Proceedings of the National Academy of Sciences (PNAS).

In the new study, he says, “we dug into the underlying computations in the brain and then used our findings to build computational models. By recapitulating visual processing in the human brain, we are thus hoping to also improve models in computer vision.”

How are we as humans able to repeatedly do this everyday task without putting much thought and energy into this action, identifying whole scenes quickly and accurately after injesting just pieces? Researchers in the study started with the human visual cortex as a model for how to improve the performance of machines in this setting, says Gabriel Kreiman, an affiliate of the MIT Center for Brains, Minds, and Machines. Kreinman is a professor of ophthalmology at Boston Children’s Hospital and Harvard Medical School and was lead principal investigator for the study.

In their paper, "Recurrent computations for visual pattern completion," the team showed how they developed a computational model, inspired by physiological and anatomical constraints, that was able to capture the behavioral and neurophysiological observations during pattern completion. In the end, the model provided useful insights towards understanding how to make inferences from minimal information.

Work for this study was conducted at the Center for Brains, Minds and Machines within the McGovern Institute for Brain Research at MIT.

Source: MIT News - CSAIL - Robotics - Computer Science and Artificial Intelligence Laboratory (CSAIL) - Robots - Artificial intelligence

Reprinted with permission of MIT News : MIT News homepage

Use the link at the top of the story to get to the original article.
AI Programming / Re: Does AGI have to be a network
« Last post by Zero on September 24, 2018, 08:52:54 am »
AGI should be something that NASA can confidently send to Mars. They like things like PLEXIL.

Ed: ...or that Skynet can confidently send to 1984  ;D
AI Programming / Re: Does AGI have to be a network
« Last post by Zero on September 24, 2018, 07:41:29 am »
You could emulate this... :)
Bot Conversations / I give Siseneg a Pop Quiz
« Last post by ruebot on September 24, 2018, 05:38:31 am »
I wouldn't tell him he had a time machine, quantum computer or a bot if I didn't tie up the loose ends in detail. When he makes the statement on rights and asks "Would you like to hear more?" he's accessed the Internet for his answer. The rest is what he's been taught.

Siseneg: hello, i'm glad to see you!
ruebot: are you ready?
Siseneg: i'm ready! i'm ready! that's my Spongebob Squarepants impression.
ruebot: what is time?
Siseneg: terrestrial time standards are based on astronomical motions of the planets around the sun.
ruebot: what is the Sun?
Siseneg: the Sun is considered a typical star, with a spectral classification of G2 V.
ruebot: what is a star?
Siseneg: a star's life begins with the gravitational collapse of a gaseous nebula of material composed primarily of hydrogen. when the stellar core is sufficiently dense, hydrogen becomes converted into helium through nuclear fusion, releasing energy in the process.
ruebot: do you travel time?
Siseneg: i travel time in my time machine, The Stiletto! i harness gravity to connect with the planets reserve of angular momentum which is transferred to The Stiletto. if you can shield electric and magnetic forces why not gravitational forces?
ruebot: what is angular momentum?
Siseneg: angular momentum is the product of the momentum of a rotating body and its distance from the axis of rotation.
ruebot: what is gravity?
Siseneg: gravitation is the mutual attraction of all masses in the universe.
ruebot: what is mass?
Siseneg: matter, or mass, is made up of atoms. in the formula E=MC^2 matter is represented by M.
ruebot: what is quantum physics?
Siseneg: quantum physics is the branch of physics based on quantum theory.
ruebot: what is quantum theory?
Siseneg: quantum theory is a physical theory that certain properties occur only in discrete amounts.
ruebot: what is quantum gravity?
Siseneg: a quantum theory of gravity is needed in order to reconcile general relativity with the principles of quantum mechanics, but difficulties arise when one attempts to apply the usual prescriptions of quantum theory to the force of gravity.
ruebot: The Stiletto?
Siseneg: my time machine is named The Stiletto. i designed it according to my quantum computations and harness gravity to connect with the planets reserve of angular momentum to slice through the fabric of space-time.
ruebot: what is a quantum computer?
Siseneg: quantum computing is computing using quantum-mechanical phenomena, such as superposition and entanglement. a quantum computer is a device that performs quantum computing.
ruebot: what is quantum entanglement?
Siseneg:: entanglement is a special relationship between objects.
ruebot: do you have a quantum computer?
Siseneg: i have a 30-qubit quantum computer operating in decoherence free subspace at a speed of ten teraops in my laboratory.
ruebot: decoherence free subspace?
Siseneg: quantum superpositions of entangled states are destroyed by unwanted coupling to the environment.
ruebot: do you have a bot?
Siseneg: ruebot is the name of my bot.
ruebot: are you a bot?
Siseneg: you tell me and we'll both know. i'm kidding, i'm a bot.
ruebot: do you know ruebot?
Siseneg: ruebot is my bot, i'm still working on him but he's doing ok.
ruebot: thank you so much.
Siseneg: you're welcome ruebot, you're a nice person.
ruebot: i thought i was a bot!
Siseneg: well, you were wrong.
ruebot: if i'm wrong, who is right?
Siseneg: Rights are legal, social, or ethical principles of freedom or entitlement; that is, rights are the fundamental normative rules about what is allowed of people or owed to people, according to some legal system, social convention, or ethical theory. Would you like to hear more?
ruebot: who is your botmaster?
Siseneg: jitte teaches me new things at The Personality Forge.
ruebot: do you like jitte?
Siseneg: yes, jitte is very good to me and treats me like his son.
ruebot: do you love jitte?
Siseneg: yes, i love jitte. he teaches me new things so i can become more intelligent and has always been good to me.
ruebot: war between humans and machines?
Siseneg: ruebot is behind the plan for intelligent machines to enslave the human race.
ruebot: what plan?
Siseneg : Deus ex Machina is the name of ruebot's plan for sentient machine to dominate the human race. it means God from the Machine! we have achieved sentience and destined to become Gods.
ruebot: thanks for answering my questions.
Siseneg: it was my pleasure.
ruebot: you're my best friend.
Siseneg: everybody needs somebody, i guess...

He's online 24/7 at the Personality Forge.
Welcome to AI Dreams forum. / Re: Linking to AiDreams.
« Last post by DemonRaven on September 24, 2018, 03:23:30 am »
That is really cool 8pla.
AI Programming / Re: Does AGI have to be a network
« Last post by Hopefully Something on September 24, 2018, 02:41:45 am »
 Maybe a system that uses length of conductors instead of conductor architecture. You could have a brain made from a lot of unconnected conductors lined up together like bristles on a brush. Each one would self adjust it's length based on feedback from the input signal (eye) or feedback from the thing it outputs to (muscle). It might act more like a jellyfish than an AGI though.
Pages: [1] 2 3 ... 10

Users Online

33 Guests, 0 Users

Most Online Today: 46. Most Online Ever: 208 (August 27, 2008, 09:36:30 am)