Re: [agi] My AGI 2019 paper draft

YKY, what stops you from implementing your ideas? Facts speak louder than words. Stefan On Tue, Jun 18, 2019, 00:51 wrote: > > Do not feel bad. There very few people on this whole planet who can > really judge a AGI paper. > > So yes, you probable were being judged by people who are not in a

Re: [agi] My AGI 2019 paper draft

   Do not feel bad. There very few people on this whole planet who can really judge a AGI paper.    So yes, you probable were being judged by people who are not in a position to judge real AGI!  I am so head in my work that only a god can judge me. --

Re: [agi] My AGI 2019 paper draft

it. It's but a moment. It'll soon pass. Now's the time you need to dig deep and show some character, which is the real purpose of education, is it not? From: YKY (Yan King Yin, 甄景贤) Sent: Monday, 17 June 2019 07:10 To: AGI Subject: Re: [agi] My AGI 2019 paper draft I am really disappointed

Re: [agi] My AGI 2019 paper draft

If ur solution is valid,  you dont need approval to get it going.    Theres no more understandable results than actually having the a.i. in action! -- Artificial General Intelligence List: AGI Permalink:

Re: [agi] My AGI 2019 paper draft

audience. Best - Jean-Paul From: YKY (Yan King Yin, 甄景贤) Sent: Monday, 17 June 2019 07:10 To: AGI Subject: Re: [agi] My AGI 2019 paper draft I am really disappointed that my AGI 2019 paper has been rejected. The reasons given by the reviewers are very superficial

Re: [agi] My AGI 2019 paper draft

I am really disappointed that my AGI 2019 paper has been rejected. The reasons given by the reviewers are very superficial and vacuous, and given that I have posted my presentation slides here which explained the theory in very simple terms, and they have not given me a chance to explain any

Re: [agi] My AGI 2019 paper draft

etworks. Agreed From: Stefan Reich via AGI Sent: Saturday, 01 June 2019 18:42 To: AGI Subject: Re: [agi] My AGI 2019 paper draft Thanks for believing that I can do this. On Sat, May 11, 2019, 18:27 Matt Mahoney mailto:mattmahone...@gmail.com>> wrote: "Conv

Re: [agi] My AGI 2019 paper draft

On 6/1/19 6:42 PM, Stefan Reich via AGI wrote: Thanks for believing that I can do this. On Sat, May 11, 2019, 18:27 Matt Mahoney > wrote: "Conventional" AI was coding all the knowledge in Lisp. Then came rule based systems and the AI winter. Neural

Re: [agi] My AGI 2019 paper draft

Thanks for believing that I can do this. On Sat, May 11, 2019, 18:27 Matt Mahoney wrote: > "Conventional" AI was coding all the knowledge in Lisp. Then came rule > based systems and the AI winter. Neural networks have produced the best > results in language, vision, and robotics, now that we

Re: [agi] My AGI 2019 paper draft

Yes, the Bellman equation and the Hamilton-Jacobi equation are just discrete and continuous versions of essentially the same idea. They are now jointly referred to as the HJB equation. I merely explored what has been known in the literature, to see if there is any advantage to be gained in the

Re: [agi] My AGI 2019 paper draft

In order to understand the problem well, suppose that everything is known, reward, state and action space, transitions. Why do you need to formulate Hamitonian formulation? I am missing this point. Do you need an optimality condition? If so, since you are working on discrete state-action sets, the

Re: [agi] My AGI 2019 paper draft

On Tue, May 14, 2019 at 9:39 PM wrote: > How would make your model walk. No demo needed for me? just simple talk > would be greatly > appreciated. > You mean learn to walk, with robotic legs? Then set up an environment, where: - input = body sensors, translated into propositions -

Re: [agi] My AGI 2019 paper draft

On Wed, May 15, 2019 at 3:42 AM Sergio VM wrote: > Not sure if I am following you... > > In order to define the optimal control problem, you need: > >- State set: Set of all possible logic propositions. OK >- Action set: Logic rules. It is not clear to me what this means. Can >you

Re: [agi] My AGI 2019 paper draft

Not sure if I am following you... In order to define the optimal control problem, you need: - State set: Set of all possible logic propositions. OK - Action set: Logic rules. It is not clear to me what this means. Can you choose which logic rule to use with which proposition? I mean,

Re: [agi] My AGI 2019 paper draft

How would make your model walk. No demo needed for me? just simple talk would be greatly  appreciated.  -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323-Mba4771b58706a18c4313c9b4 Delivery

Re: [agi] My AGI 2019 paper draft

On Sun, May 12, 2019 at 10:22 PM Sergio VM wrote: > Hi King Yin, > > The architecture looks very interesting. I am just missing the definition > of the reward function (or kernel if you make it stochastic). > > On the other hand, I don't understand your previous comment on the > Lagrangian and

Re: [agi] My AGI 2019 paper draft

Nice slides... thanks for the help ill tip you from where I sit. Yes the search, is a nice alternative for the ai problem,  but its too expensive,   and for some reason no-one has a quantum computer yet.   If you did have NP power tho,   theres 3 more problems as I see it. a) You must have a

Re: [agi] My AGI 2019 paper draft

Hi King Yin, The architecture looks very interesting. I am just missing the definition of the reward function (or kernel if you make it stochastic). On the other hand, I don't understand your previous comment on the Lagrangian and Hamiltonian. I haven't seen the previous version of the paper.

Re: [agi] My AGI 2019 paper draft

I think its a good thing,   need diversity, otherwise things get a little drab and over discussed. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323-M86eb314888de44bf7c1cc3e7 Delivery options:

Re: [agi] My AGI 2019 paper draft

"Conventional" AI was coding all the knowledge in Lisp. Then came rule based systems and the AI winter. Neural networks have produced the best results in language, vision, and robotics, now that we have enough computing power to implement them. Now we have real progress in AI. It will be

Re: [agi] My AGI 2019 paper draft

I think you are stuck in the "conventional theory". The time is right for new theories. I'm still on the path to show that there are better ways to actual AI than neural networks. On Sat, May 11, 2019, 08:46 YKY (Yan King Yin, 甄景贤) < generic.intellige...@gmail.com> wrote: > Also, the control

Re: [agi] My AGI 2019 paper draft

Looking 3 moves ahead in chess, counts for a lot more than looking 3 moves ahead if your walking down the street. =D -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323-M07a1c8ac9ad7b0e321740276

Re: [agi] My AGI 2019 paper draft

Also, the control theoretic stuff was removed because I am unable to define the reward based on the current state in a *differentiable* way. For example, in the game of chess, the reward comes only when checkmate occurs (according to the game's official rules), but not when you capture a piece of

Re: [agi] My AGI 2019 paper draft

Thanks for the encouraging words  I have presented my theory to a Chinese AGI group and got some positive feedback also. I will translate my slides into English. The slides explain the theory in an easier and more friendly way. Also, the RNN-within-RNN architecture is still inefficient and I

Re: [agi] My AGI 2019 paper draft

Reread the paper, it makes more sense the more times you read it: "The main idea is to regard “thinking” as a dynamical system operating on mental states:" Then think about how the system would learn to drive a car, for example... then learn to fly an airplane. John

Re: [agi] My AGI 2019 paper draft

generally and/or specifically… IMO this where the multi-agent >> consciousness mechanics come in but I’ll shield some eyes on that one :) >> >> >> >> John >> >> >> >> *From:* Stefan Reich via AGI >> *Sent:* Friday, April 19, 2019 4:21

RE: [agi] My AGI 2019 paper draft

hanics come in but I’ll shield some eyes on that one :) John From: Stefan Reich via AGI Sent: Friday, April 19, 2019 4:21 PM To: AGI Subject: Re: [agi] My AGI 2019 paper draft Good review On Fri, Apr 19, 2019, 22:02 Matt Mahoney mailto:mattmahone...@gmail.com> > wrote: It

Re: [agi] My AGI 2019 paper draft

Good review On Fri, Apr 19, 2019, 22:02 Matt Mahoney wrote: > It would help to get your paper published if it had an experimental > results section. How do you propose to test your system? How do you plan to > compare the output with prior work on comparable systems? What will you > measure?

Re: [agi] My AGI 2019 paper draft

It would help to get your paper published if it had an experimental results section. How do you propose to test your system? How do you plan to compare the output with prior work on comparable systems? What will you measure? What benchmarks will you use (for example, image recognition, text

[agi] My AGI 2019 paper draft

Hi, This is my latest draft paper: https://drive.google.com/open?id=12v_gMtq4GzNtu1kUn9MundMc6OEhJdS8 I submitted the same basic idea in AGI 2016, but was rejected by some rather superficial reasons. At that time, reinforcement learning for AI was not widely heard of, but since then it has