Recent Posts

Pages: 1 ... 8 9 [10]
Theory and Discussion / Re: What is ARTUR?
« Last post by Paul on April 20, 2018, 08:29:01 AM »
I've been quite here on the forum for a while (mainly been active on the Numenta forum).  Thought I would post a progress update.

I spent some time on the Reinforcement Learning problem, and linking it with HTM (which still I believe is the best starting technology for the seed AI).  About this time last year I formalized a strategy, which I described in this thread .  For reference, here is a visualization of that strategy:

I've since discovered a couple of problems with this strategy.

One issue is with the reinforcement TP layer.  The basic problem here is that although the pooling layer creates a representation depicting all expected future rewards/punishments, the result is that the system picks a future motor command with the most reward (skipping required previous motor commands).  I spent some times putting in hacks to get around this, but think I need to tackle the problem from a different angle.

I've been reading neuroscience papers to see if I can get clues from biology.  One interesting paper is Computational Cognitive Neuroscience.  An important clue is this diagram:

The dynamics columns are the key here.  What I have developed so far models only an "integrator" dynamic.  For the reinforcement learning problem, leveraging a "separator" dynamic is necessary.  I've started looking more closely at a thesis paper by Ali Kaan Sungur, who has modeled the basal ganglia and integrated with HTM.

The second issue is that the location signal is kind of a magic box without any description of where it comes from.  For testing, it can be hard-coded, but it needs to be replaced with something generic.  The latest HTM School video introduces the concept of grid cells, which is definitely the correct starting point to solving this problem.  I've also been keeping up with Numenta's work in this area.  Jeff's recent talk at Simons Institute highlights their latest thinking in the current round of research.  The relevant connections:

I've also begun working on a new implementation of HTM in GoLang, which allows for multi-core processing, or distributed processing over a network.  The basic design looks like this:

The basic idea is to integrate a cluster of shards which each process a sub-set of cells or minicolumns in parallel, and assemble their outputs into a completed SDR. This is done by a leveraging a module I'm calling the Sparse Representation Controller (SRC) which takes chunks of a representation and reassembles them:

An SRC acts as a message bus with receivers and transmitters. Shards that need to know complete activation SDRs register as receivers, and related shards register as transmitters to report their output. Once an SRC receives all outputs from transmitting shards, it constructs an activation SDR and transmits it to all registered receivers. Because only the resulting activation SDR is transmitted, the size of traffic within the cluster is small, and most of the processing within a shard can happen in parallel with a relatively small window required for synchronization.

The SRC for Spatial Pooling is a special case, because it needs to coordinate scoring across all shards.  I've called this special SRC the Spatial Pooling Controller (SPC).  The amount of traffic transmitted within a spatial pooling cluster is reduced by having the SP shards only report their top (sparsity * shard count) scores to the SPC. The SPC joins those and clips to just the top (sparsity) minicolumns. It then reports back only those winners which are relevant to each shard for learning.
Support / Re: Help with 7z mupen64plus fz.
« Last post by fzurita on April 20, 2018, 07:01:03 AM »
I think I see a problem. Do your zip or 7zip files contain files that are not ROMs?
Support / Re: Help with 7z mupen64plus fz.
« Last post by fzurita on April 20, 2018, 12:20:49 AM »
I just tried it with a zip file and it worked ok. Is the problem only with 7zip?
Miscellaneous / ARTUR Exmachina
« Last post by Pocky on April 19, 2018, 06:53:01 PM »
The ARTUR project and discussion Paul is working on makes me think of Exmachina. Curiosity was a huge element that drove the AI.
Support / Re: Help with 7z mupen64plus fz.
« Last post by Unmecbien on April 17, 2018, 02:02:54 PM »
Thx hope u can fix it GL  :)
Support / Re: Optimization for Galaxy S8
« Last post by fzurita on April 17, 2018, 01:21:39 PM »
Once you have the game open, open up the sidebar, scroll down to controller paks, and switch the controller pak to "Rumble Pak"
Support / Re: Help with 7z mupen64plus fz.
« Last post by fzurita on April 17, 2018, 01:20:25 PM »
Hmm.. interesting, this could be a bug. I'll look into it.
Support / Help with 7z mupen64plus fz.
« Last post by Unmecbien on April 17, 2018, 05:48:08 AM »
Hello everyone, I need help, I have a gpd xd plus and emulator mupen64plus fz 3.0.181(beta).
I use Arc browser to launch my games.
When I run a non-compressing game ".n64" everything works fine, but if I run the same game compress in "7z" emulator launches but the game no, can you help me please, in arc browser the parameters to send to emulator is:% rom_uri% can you optimize it?.
i try with a game in 'zip' same probleme.
thx for ur help i'm french my english is very bad, hope u can undestand my probleme.
Support / Re: Optimization for Galaxy S8
« Last post by nonosto on April 16, 2018, 10:38:42 PM »
THX very much. Last thing how to run rumble from phone with compatible game please?
Support / Re: Optimization for Galaxy S8
« Last post by fzurita on April 15, 2018, 02:00:15 PM »
About thing, for your phone, I would try using GLideN64-Accurate emulation profile.
Pages: 1 ... 8 9 [10]