On Thursday, April 22, 2021, at 5:22 PM, stefan.reich.maker.of.eye wrote:
> PS: Topicbox web interface really bugs with inline images. The Post button
> just keeps rotating forever. Anyone to report this to?
Stefan, I'm sure the feedback would help them:
Noun verb object. Basis of everything.
https://botcompany.de/images/1102982
PS: Topicbox web interface really bugs with inline images. The Post button just
keeps rotating forever. Anyone to report this to?
--
Artificial General Intelligence List: AGI
On Thursday, April 22, 2021, at 3:59 PM, Matt Mahoney wrote:
> Sort of. A FFT requires dividing up the audio samples into blocks. The
> cochlea instead applies bandpass filters to produce an array of continuous
> signals.
Is there a standard algorithm for doing the same thing in place of an FFT?
On Thu, Apr 22, 2021 at 8:54 AM Matt Mahoney
wrote:
> ... You can't test for consciousness.
>
That depends on how you define it. Who has pulled a Shane Legg on
"definitions of consciousness" the way he did on definitions of
intelligence?
> It is common to expand data to compress better.
>
The Northwest AGI Forum is pleased and honored to welcome ACM
Distinguished Speaker Dr. Antonio Lieto to present his book:
"Cognitive Design for Artificial Minds"
https://www.amazon.com/dp/1138207950
***
Where: Zoom only (Seattle area meetup)
When: Apr 28, 2021, 8:30 a.m. Pacific Time
When I said "who will last longer, the one building AGI to shoot clouds or to
shoot enemies", I really meant meteors/ aging/ etc, cuz obviously you know my
point is things change and all that lasts in the long run is the survivors, not
the ones just playing with AGI...we use cars /etc all in a
A 2nd use of the word compress exists here though - yes brains do compress data
into a brain, lookup Trie Tree. This allows the brain to make new predictions
that are correct. It also allows you to compress a file by storing the errors
in your predictions as a long code so upon decompression
On Thu, Apr 22, 2021, 9:46 AM stefan.reich.maker.of.eye via AGI <
agi@agi.topicbox.com> wrote:
> I always thought that an FFT is the most likely first step in speech
> recognition, seeing as you can almost recognize it visually from a 2D
> frequency/time plot as a human.
>
Sort of. A FFT
Just a few comments on this thread. The difference between predicting and
understanding is that one requires consciousness. In other words, there is
no difference. We use prediction to test understanding. You can't test for
consciousness.
Brains don't compress, they predict. You can only compress
I always thought that an FFT is the most likely first step in speech
recognition, seeing as you can almost recognize it visually from a 2D
frequency/time plot as a human.
--
Artificial General Intelligence List: AGI
Permalink:
There are no vectors in the use of CNNs to detect spoken keywords that I
mentioned in the first post. I only mentioned vector spaces after
immortal.discoveries mentioned something about recognition of various sizes. I
guess bringing vector spaces into the discussion was a mistake on my part. I
11 matches
Mail list logo