" Maybe you didn't understand me Danko. To say it again: It's not about which system/machine is more general or better, it's about what plays out in physics of Earth. "
I think you are not taking into account the fact that 1) logistic regression, decision tree and a convolutional neural network all work with the physics of Earth, and still 2) the no-free-lunch theorem applies to them (in daily usage). Otherwise, we would have only one machine learning algorithm, not multiple ones. Each of them works better in one situation and worse in another. What does that imply. This implies that yes, of course, being limited to the physics on Earth limits the set of possible algorithms that will apply. However, this reduction is not sufficient to be able to device an algorithm that is efficient with all the problems on the planet Earth. The problem that NFL theorem describes, remains still with the physics on planet Earth. By restricting yourself to Earth, you are only reducing your previously bigger space of infinities to a smaller space of infinities. But you still stay with infinities--even with the physics on the plant Earth. That is, if you move from infinity to a power of billion down to infinity to a power of million, you have made quite a reduction. Unfortunately, this is not enough to get you anywhere because you are still left with a huge space of possible problems (and possible models for those problems) that you cannot resolve with a single algorithm. On Tue, Feb 4, 2020 at 12:18 AM <immortal.discover...@gmail.com> wrote: > Maybe you didn't understand me Danko. To say it again: It's not about > which system/machine is more general or better, it's about what plays out > in physics of Earth. Larger systems that have more patterns and regenerate > faster overtake the land. The power behind what Does happen is in the > amount of sorted context a system has and it's ability to regenerate itself > faster. > > The free lunch is when you have an optimal set of organs; a violinist, a > mechanic, a waiter, a receptionist, a cleaner, a storage boy, the global > result is best just-right based on the even balance of the littler parts. > So it is now 'best' using these organs that are not good at all things. > What is best mean? Good. What does Good mean? Survival. So what happens in > the end is Survival, it finds the just right set of organs at all levels. > *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/T353f2000d499d93b-M414e2042290c4b157bae5c5b> > -- Prof. Dr. Danko Nikolić www.danko-nikolic.com https://www.linkedin.com/in/danko-nikolic/ ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T353f2000d499d93b-M9c9ddf41cf9a3a3e9102bccb Delivery options: https://agi.topicbox.com/groups/agi/subscription
