> Sound is almost certainly easier sensory data to process than visual, > primarily because it is processed as parallel one-dimensional streams > (in the brain and often in computers, but a good idea in the abstract) > rather than trying to map a 2+ dimensional field like vision. Sound > makes a good progression, in terms of complexity, from something like > text which is a single one-dimensional stream. > > The format of sound should be similar to how the human brain gets it, > mostly because it makes a lot of sense generally. Take the audio signal > and split it into multiple spectral bands at regular intervals, the data > to be processed being streams that contain changes in amplitude in a > specific spectral band. > > If you want to make it low cost but still fully capable of handling > things like human speech, I would suggest the following: > > - Low-pass filter the source at 8kHz > - 32 to 64 spectral channels > - 10ms update intervals > > You could get good results with even lower resolution than this, but the > above should keep things well-above the conversion artifact noise floor > for almost any experiment with sound you want to do. Any vaguely modern > CPU could do this conversion in realtime without even breaking a sweat, > particularly if offloaded to a vector processor.
Last time I checked, speech recognition still performed badly. I guess the audio "resolution" has to be drastically reduced just like in video. The purpose of audio is to make the sensorium as close to human's as possible. [Ben: While embodiment is not required for *intelligence* per se, it is probably very useful if we want to create the *contents* of human-like cognition, eg if we want the AGI to understand natural language and texts. > > ATTENTION > > ========= > > It should also contain an "attention" input which specifies > > what kind of information should be focused on. Examples: > > This is an input? I would think that the point is to grab the attention > of the system i.e. play to adaptive (or not so adaptive) biases in its > pattern filtering, which I presume all reasonable AGI systems have. You're talking about the AGI's internal allocation of attention, which is a high-level mechanism. The visual frontend does not "know" where to direct its attention, it needs to be told, IMO. Therefore the focus of attention is an input. Also, this trick IMO will be very important for speeding up visual processing. > > KNOWLEDGE EXCHANGE > > ================== > > This is a more ambitious feature. I want to create a protocol > > for exchanging knowledge that are learned from different robots. > > For example one person can train his robot to recognize fruits > > and another trains his for faces. Then a web server may provide > > tools to maintain a database of such "knowledge" files as well > > as tools to merge them, etc. > > I don't see how this is generally possible, short of playing a source > data log forward. I mean, I can merge and share the knowledge of MY > systems(1), but any representation I use is reflective of the > assumptions and theory of my model and may have no possible or easy or > tractable translation into the representation of of another model. This > is not an easy problem to work around in a really functional way. The > capability to load the "brain" of one system into another is very useful > and doable, but it won't translate well outside of a single system design. > > I expect when AGI-ish technologies start to take off, there will be huge > trade and commerce in loadable modules that contain certain classes of > experience and knowledge. > > > (1): The other caveat is that any system/representation merge that isn't > exhaustive (i.e. summing to systems together in totality) will > necessarily lose a lot of pattern context that is probably relevant. On > the upside, a fully merged system generally uses fewer resources than > the sum of the two independent systems that went into the merged system. > Size has its advantages. If you're talking about knowledge exchange for complete systems, I agree that is nearly impossible. Knowledge can only be exchanged within instances of the same system. I'm only proposing KX for the sensory frontend. It looks like there's going to be a battle of "KX standards" among various AGIs... all the more reasons to think about this problem sooner. YKY -- _______________________________________________ Find what you are looking for with the Lycos Yellow Pages http://r.lycos.com/r/yp_emailfooter/http://yellowpages.lycos.com/default.asp?SRC=lycos10 ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
