Re: [agi] Do Neural Networks Need To Think Like Humans?

The brain inspires a new type of artificial intelligence: https://techxplore.com/news/2019-08-brain-artificial-intelligence.html   -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

  Mad Max: Affine Spline Insights into Deep Learning: https://www.youtube.com/watch?v=7Q2JhZxNPow -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-M6cd7aaee02b2a8f831c54dca Delivery options:

Re: [agi] Do Neural Networks Need To Think Like Humans?

On 5/30/19 4:09 AM, keghnf...@gmail.com wrote:  The technology is not for free. If a humanitarian give me a ten million $ i will share it with the world. If some one give me hundred million $  i will share the work just between us. Unless you make a free software or open source AGI system.

Re: [agi] Do Neural Networks Need To Think Like Humans?

 The technology is not for free. If a humanitarian give me a ten million $ i will share it with the world.  If some one give me hundred million $  i will share the work just between us.   -- Artificial General Intelligence List: AGI Permalink:

Re: Re: [agi] Do Neural Networks Need To Think Like Humans?

OK, I will check your work in detail.thanks very much. JZTANG ZJU From: keghnfeem Date: 2019-05-29 21:09 To: AGI Subject: Re: [agi] Do Neural Networks Need To Think Like Humans? I tell you this, my way is not minor direction toward AGI. I have a complete model and theory. The data my system

Re: [agi] Do Neural Networks Need To Think Like Humans?

 I tell you this, my way is not minor direction toward AGI. I have a complete model and theory.  The data my system uses is video data. And is completely unsupervised.  https://groups.google.com/forum/#!topic/artificial-general-intelligence/0rHVcqNoFG8  My AGI system will learn only from the

Re: Re: [agi] Do Neural Networks Need To Think Like Humans?

I think your way is a minor step toward right direction. However , it should be totally unsupervised. Knowledge should be gradually developed though intraction with enviroment. JZTANG ZJU From: keghnfeem Date: 2019-05-28 21:28 To: AGI Subject: Re: [agi] Do Neural Networks Need To Think

Re: [agi] Do Neural Networks Need To Think Like Humans?

As below; but then the Flat-Earthers... https://singularityhub.com/2019/05/20/an-ai-for-image-recognition-spontaneously-gained-a-number-sense/ On 28.05.2019 11:22, jzt...@zju.edu.cn wrote: i am trying to develop a new architecture; a system that works like human should have simple princilpe.

Re: [agi] Do Neural Networks Need To Think Like Humans?

@jztang i am working on this. It is a unsupervised RNN GAN.  i call it un-Gan.  Vicarious has part of it which is a supervised version:  https://www.vicarious.com/2017/10/26/common-sense-cortex-and-captcha/ -- Artificial General Intelligence List: AGI

Re: [agi] Do Neural Networks Need To Think Like Humans?

I think neural network can't be used to develop AGI.  A system that think like humans must adapt to a real envrioment, to get and absorb information from enviroment.  JZTANG ZJU -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

  The sliding kernel, of a CNN, is doing polar regression and or spline smoothing on edges, in a indirect way! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-M756f5f0da6106e1b905c7846 Delivery

Re: [agi] Do Neural Networks Need To Think Like Humans?

the brain has to deal with LOTS of hidden variables. Thats why it MUST be approximate - because a computer trying to simulate everything in detail is ALSO impossible!  So the real ai, artificial even, still needs to be approximate, but also true. If you were to simulate a car running,  you have

Re: [agi] Do Neural Networks Need To Think Like Humans?

Results of a recent "Imperfect Bayesian inference in visual perception study” suggest that "perception is founded on Bayesian principles, but with suboptimalities in the implementation of these principles. The view of perception as imperfect Bayesian inference can provide a middle ground

Re: [agi] Do Neural Networks Need To Think Like Humans?

I think neural nets have to think LESS like humans.   just get the job done,  nature is a time wasting inefficiency, you dont need it AT ALL. -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

Neuroscientists identify a brain circuit that helps break complex decisions down into smaller pieces: https://medicalxpress.com/news/2019-05-neuroscientists-brain-circuit-complex-decisions.html -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

https://discourse-cdn-sjc2.com/standard14/uploads/numenta/original/2X/a/ad7f6f69320c727050a925b58d03fa87f8f1.png -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-M74bfb4865da5eb903cb63ef1

Re: [agi] Do Neural Networks Need To Think Like Humans?

The inferotemporal cortex is key to differentiating between objects:  https://medicalxpress.com/news/2019-03-inferotemporal-cortex-key-differentiating.html -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

Thanks Jim. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-M50559774e050d8b77d141409 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] Do Neural Networks Need To Think Like Humans?

Although the Activation Atlas is a little misleading (in my opinion), it has given me some vague ideas about how a symbol net might work. Jim Bromer On Wed, Mar 13, 2019 at 8:18 PM Jim Bromer wrote: > Great article. Thanks again. > Jim Bromer > > > On Tue, Mar 12, 2019 at 6:28 PM wrote: > >>

Re: [agi] Do Neural Networks Need To Think Like Humans?

Great article. Thanks again. Jim Bromer On Tue, Mar 12, 2019 at 6:28 PM wrote: > > Exploring Neural Networks with Activation Atlases: > > > > https://distill.pub/2019/activation-atlas/?utm_campaign=Data_Elixir_medium=email_source=Data_Elixir_224 > *Artificial General Intelligence List

Re: [agi] Do Neural Networks Need To Think Like Humans?

 That is very true Stefan. Detector NN have layers of where simple features are generally  in the first layers of the NN. And complex feature are detector are in  the later part. There is bit of play in applying the back propagation algorithm during training  so that complex detection and simple

Re: [agi] Do Neural Networks Need To Think Like Humans?

Exploring Neural Networks with Activation Atlases:  https://distill.pub/2019/activation-atlas/?utm_campaign=Data_Elixir_medium=email_source=Data_Elixir_224 -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

I agree too. That the edges are key to AGI. But it just shows how flexible NN can be.   My AGI model and theories parallels in a lot of ways to Korrelan's. Hello Korrelan. But there are great difference in other parts of my model and Korrealan's. So yes in my work i am using a attention

Re: [agi] Do Neural Networks Need To Think Like Humans?

@Matt - I agree. This is a AGI ocular input module, at the end of the video you can see the results from using a polar retina, high resolution fovea and the peripheral degrading lower resolutions.  There are videos showing the negation of rotational/ scale invariance using the same technique.

Re: [agi] Do Neural Networks Need To Think Like Humans?

What this 2 minute video seems to show is that neural networks need to see more like humans to detect shapes rather than just textures. Our visual cortex detects lines, edges, and other regions of high contrast in several layers. But we see shapes by moving the fovea along a path connecting these

Re: [agi] Do Neural Networks Need To Think Like Humans?

'How neural networks learn' - Part III: The learning dynamics behind generalization and overfitting: https://www.youtube.com/watch?v=pFWiauHOFpY -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] Do Neural Networks Need To Think Like Humans?

This was really interesting. Jim Bromer On Sat, Mar 9, 2019 at 10:09 AM wrote: > Do Neural Networks Need To Think Like Humans?: > > > https://www.youtube.com/watch?v=YFL-MI5xzgg > *Artificial General Intelligence List * > / AGI / see discussions