Dear Yan King Yin Thank you for sharing. From what I understood, you're doing a great job as a scientist.
That which you say cannot be done in entangled polynomial gestalt (as form-to-function), is more holistic. I disagree with your assertion. I think you should develop that train of thought more as real possibility. My theory enables fractal learning, but it's going to be a huge job to code the theory into a functional, recursive software platform. I'm not going to personally be able to do that in my lifetime. I'm still developing the theory for an AGI architecture. I do believe that I've recently made a conceptual breakthrough on how to control quantum entanglement in action, but I need to work on that a lot more. As far as I can see, almost all your assumptions are on track. Those who are not, are the ones stopping your progress. I'd suggest you concentrate some more on thermodynamics and NP Hard. The halting problem may be addressable with quantum design. Change all your assumptions to possibilities and start writing down the rules. That is the space you need to create for all possible logic. Rules without logic, is noise. Keep at it. You're going to get there. Benjamin Robert ________________________________ From: YKY (Yan King Yin, ็ๆฏ่ดค) <[email protected]> Sent: Thursday, 19 December 2019 06:17 To: AGI <[email protected]> Subject: [agi] On AGI architecture This set of slides were written in September, just after the AGI 2019 Conference in China, but I only got time to translate them into English today: English version: https://drive.google.com/open?id=1J9_rihrWWXvQE1-wTz5iXOXhdnHpK7Wx Chinese version: https://drive.google.com/open?id=1IGfRaUc-uSSEca2D-mwF5T05JRfxUVg7 One contribution I'm quite proud of is that reinforcement learning can be viewed as solving the Schrodinger equation. Though it may not be of very high practical value ๐ I'm currently designing an AGI architecture borrowing ideas from Google's BERT. I will explain this in another set of slides. Comments and suggestions welcome ๐ Artificial General Intelligence List<https://agi.topicbox.com/latest> / AGI / see discussions<https://agi.topicbox.com/groups/agi> + participants<https://agi.topicbox.com/groups/agi/members> + delivery options<https://agi.topicbox.com/groups/agi/subscription> Permalink<https://agi.topicbox.com/groups/agi/Tcfe7cc93841eec23-M5e1415728f77e7318ae0daed> ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tcfe7cc93841eec23-M22e60f8d0b98bd36f1a25364 Delivery options: https://agi.topicbox.com/groups/agi/subscription
