Evolution did it's Random Search

This is an evolutionary perspective on intelligence. No matter for natural or artificial intelligence, I believe that there exist, certain "correct" ways of information processing and decision making mechanism that makes "intellience". It just happens that the random search conducted by evolution found such mechanism and presented in the form of our brain. As long as natural intelligence remains as the best form of intellignece, it keep inform us about hwo to get closer to true mechnism of intelligence.

To some extent, machine learning is just about feature learning \(\vec \phi(\vec x)\), trying to find a correct mathamatical space (may be very complex, may involve going to the weight world to find correct projection, or may involve projecting to infinite dimension to find representation), a feature space \(\Phi\), to allow \(X\) project onto and reveal some hidden structure. Inspired by professor Justin Eldridge from UCSD data science: the math itself for learning to occur may not be as complicated, it is rather the underlaying structure of the data that exist in nature promotes the stemming of intelligence, we just need to find such structure, a correct representation of \(X\). Finding intelligence stemming from biology may also just need to find such correct subspace.

Inspired by professor Talmo Pereira from the Salk Institute, nature has creative solutions to match objective functions caused by evolution and there exists a strong coupling between such natural behavior and the underlying neural algorithm. The neural underpinning that we have just happens to be the information processing theory that works because it helps survival to pass on the genes. Most of the times something that seems to be "intelligent" are just things that happens to do the right things that works. A great deal of neuronal mechanism is about our output, our actions, and our interaction with the environment: it is about what we do. I think that finding the right layer of abstractions and injecting the baisc alignment with biology into artificial agents would go beyond the limits of human-interpretable labels and power searches into the correct representations to inform us about how to build abstract models of the brain and get closer to the hypothesis of “intelligence”.