Super-Intelligent Machines - A Mathematical Approach
My feed today showed this paper published by Buehrer and colleagues (2017) with respect to a mathematical framework for superintelligent machines.
Leaving the sophisticated title aside, their paper is about a class calculus expressive enough for self-learning optimization (it is capable of describing and improving its learning process). As specified in the paper:
"It can design and debug programs that satisfy given input/output constraints, base d on its ontology of previously learned programs. It can improve its own model of the world by checking the actual results of the actions of its robotic activators." [source]
Some potential applications and examples to which this abstract concept can be used for are (as they suggest):
- check the black-box of a crashed car to determine the reason of the crash:
"...if it was probably caused by electric failure, a stuck electronic gate, dark ice, or some other condition that it must add to its ontology in order to meet its sub-goal of preventing such crashes in the future." [source]
Now, to nudge you and to provide some sort of interest for reading the paper and maybe understanding some of its implications is that the paper is a description of something called 'The Master Algorithm' - by machine learning researcher Pedro Dominguez. Now you're interested?
To stay in touch with me, follow @cristi
Cristi Vlad Self-Experimenter and Author
Well I’m gonna start talking in relation to {AI} Artificial intelligence has contributed greatly to the growth of humanity. Some says it’s the future and some says the machines will someday become aware of the environment and their existence and take
On a tv show showing the future as brought to limelight a micro sensor in form of particle and with multiples of it forming colony of sensors in particles that could feel it environments and transmit information to others across the city forming a gigantic network that could instantly report any change in the environment. These particles could be mixed with concrete for building and roads. Imagine your building a colony of sensors and the roads leading to your garage all are alive and receiving and sending data about your environment.
The creation of any AI is impossible in the absence of mathematics and physics. Thanks for impacting
what's the show called?
The Next World{ Future technologies }on DSTV on one of the discovery channels .
Took a look at the abstract and the introduction and I think I get the general idea. Nothing specific comes to mind as of now but perhaps after taking a longer look, it might trigger something........
Would be leaving for the weekend so have a nice weekend and see you next week!
Have a great one!
How is this different from current neural network efforts and optimizers? Sounds useful for generating code, that consume rest apis.
different? Not necessarily. I think it could complement the current state of the orders.
Good post interesting read, thanks for sharing
