Hi Danko
Tricky question. I think the a-linear properties of general intelligence have
the potential to contradict NFL.
I don't see that as being a significant problem for the development of AGI.
I've probably spent the last 22 years working in this space. As posited, NFL
presents as a hard
On Tue, Feb 4, 2020, 4:12 PM Danko Nikolic wrote:
> " If there was no free lunch, then all the particles in the universe would
> have the same laws or random laws. "
>
> This is not true. There is no-free-lunch in everyday application of
> machine learning. When one finds out that one type of
As soon as we find a better AI than deep learning and markov models, it'll be
"good" across many datasets, like we are lol. A larger system can have more
context, so yes a larger brain will always be smarter than a smaller but as
high-tech brain, they are same tech but one has more data/speed.
You say one model performs great on real life dataset A but poorly on another
such B, while another model performs great on B but poorly on A. Take a look at
what your meaning of Great and Poorly mean. There is indeed a certain
model/brain that is the Better Great one we seek/want over all
On Tue, Feb 4, 2020, 8:26 AM stefan.reich.maker.of.eye via AGI <
agi@agi.topicbox.com> wrote:
> > It means predicting text as well as a human.
>
> So you would basically design blank-space test (a text with missing
> words), check how well humans do on that one and then do the same with
>
" If there was no free lunch, then all the particles in the universe would
have the same laws or random laws. "
This is not true. There is no-free-lunch in everyday application of machine
learning. When one finds out that one type of model performs better than
another type of model (e.g., Bayes
No Stefan, we know humans are really good predictors, the actual test is to
make a really good predictor for text so that your compression is extremely
high and so that it usually has a high probability for the next letter or bit
to predict that it should predict during decompression in a
Last night I came up with a short way to say my point: If there was no free
lunch, then all the particles in the universe would have the same laws or
random laws. What I mean is physics works a certain way, Earth is evolving a
certain way, and this path that it favors is the Ride we get for
Ben,
Links to both Arthur Franz’s video and slides are on the AGI-19 website here:
http://agi-conf.org/2019/schedule/
—matt
> On Feb 4, 2020, at 5:01 AM, Ben Goertzel wrote:
>
> See also Arthur Franz's work on biasing AIXI (Hutter's
> infinite-resources theoretical totally general AGI)
"It was more of just a thing to say to counteract the general saying which I
don't like. Being born was a free lunch, I didn't pay for it!
Oh wait, and I didn't pay for meals the next years either. So there are free
lunches!"
*Somebody* paid for your birth, and all those lunches. It just
International Conference on Artificial Intelligence and Big Data (AIBD
2020)April 25~26, 2020, Copenhagen,
Denmarkhttps://acsty2020.org/aibd/index.htmlScopeInternational Conference on
Artificial Intelligence and Big Data (AIBD 2020) will provide an excellent
international forum for sharing
https://sourceforge.net/p/maxima/mailman/message/36324684/
Excerpting from a protracted discussion to a question I had about Maxima's
"Simplify" options:
> Go's 19x19 board permits 3 states per position resulting in the equivalent
> of 572 bits of information. A mathematical expression using 6
I'll buy you a lunch if we ever meet in person. So, you can count this one
too.
Danko
On Tue, Feb 4, 2020 at 2:31 PM stefan.reich.maker.of.eye via AGI <
agi@agi.topicbox.com> wrote:
> > Please tell me about the best one you had.
>
> It was more of just a thing to say to counteract the general
Expending energy to get more energy.
Expending energy to reduce the lose of energy.
NFL explained in two lines.
--
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T353f2000d499d93b-M499012e817b9628258280476
Delivery
> Please tell me about the best one you had.
It was more of just a thing to say to counteract the general saying which I
don't like. Being born was a free lunch, I didn't pay for it!
Oh wait, and I didn't pay for meals the next years either. So there are free
lunches!
> Ignore Stefan :-D
What? I was the first one to criticize the "theorem". It's a trivially true
observation about fully random sequences, isn't it? Which are not of particular
interest, as ALL WE DO in AI is look at NON random sequences. Or am I confused
here?
> It means predicting text as well as a human.
So you would basically design blank-space test (a text with missing words),
check how well humans do on that one and then do the same with computers.
Are any of those tests online?
--
Artificial General
See also Arthur Franz's work on biasing AIXI (Hutter's
infinite-resources theoretical totally general AGI) toward our
physical universe. He gave a great talk on this at AGI-19 in
Shenzhen in August, and the video may unfortunately not be online yet,
but I think he has a PDF paper on this posted
Hi Ben,
Thanks for that information. Let me mull over it.
Danko
On Tue, Feb 4, 2020 at 9:57 AM Ben Goertzel wrote:
> Are you familiar with Marcus Hutter's work on Universal AI?
>
> The general message there is: Truly, fully general intelligence is
> only feasible with infinite computing
On Monday, February 03, 2020, at 3:32 PM, Matt Mahoney wrote:
> Less than 8.7 x 10^244 bits. That's the square of the Bekenstein bound of a
> black hole with a Schwartzchild radius equal to the Hubble radius,13.8
> billion light years. Edit distance expressed as the shortest program that
>
Are you familiar with Marcus Hutter's work on Universal AI?
The general message there is: Truly, fully general intelligence is
only feasible with infinite computing power.
However, that's not really what matters in our physical universe, let
alone in the human world here on Earth...
Eons ago I
" Maybe you didn't understand me Danko. To say it again: It's not about
which system/machine is more general or better, it's about what plays out
in physics of Earth."
I think you are not taking into account the fact that 1) logistic
regression, decision tree and a convolutional neural
You say: " i dont believe there isnt a solution " and " there is
solutions ". But this is what theorems do--they tell you that a statement
is valid for a broad range of conditions without you having to go try every
single condition. For example, Pythagora's theorem tells you that in a
triangle, c2
23 matches
Mail list logo