Author: Amir massoud Farahmand

“To the best of the author’s knowledge …” = “WE WERE TOO LAZY TO DO A REAL LITERATURE SEARCH.”
“Results were found through direct experimentation.” = “WE PLAYED AROUND WITH IT UNTIL IT WORKED.”
“The data agreed quite well with the predicted model.” = “IF YOU TURN THE PAGE UPSIDE DOWN AND SQUINT, IT DOESN’T LOOK TOO DIFFERENT.”
“It should be noted that …” = “OK, SO MY EXPERIMENTS WEREN’T PERFECT. ARE YOU HAPPY NOW??”
“There results suggest that …” = “IF WE TAKE A HUGE LEAP IN REASONING, WE CAN GET MORE MILEAGE OUT OF OUR DATA.”
“Future work will focus on … “ = “YES, WE KNOW THERE IS A BIG FLAW, BUT WE PROMISE WE’LL GET TO IT SOMEDAY.”
“…remains an open question.” = “WE HAVE NO CLUE EITHER”.

(copied from a comic from www.phdcomics.com, drawn by Jorge Cham if I read it right!)

I’ve started ranking schools with AI researches. My emphasize is on new-age AI, e.g. situated embodied intelligent robots, neural networks, machine learning (especially reinforcement learning) fuzzy systems, evolutionary computation, pattern recognition, vision, and … . It means that I do not score schools with symbolic AI approach much. In other words, I score universities which is along my preferences. I’ve divided schools into these 6 categories:

5: Everything is pleasant: good projects, good professors, good reputation of school.
4: Very good place; may be not too prestigious.
3: Somehow good, e.g. one or two well-known professors but not a famous school.
2: Hey! There are trying to do something!
1: There is a little AI there, i.e. just having the name.
0: Nothing!

I will report the results after finishing my applying and receiving admissions. Universities can increase their rank by giving me admission with financial aid!

Hey! Is there anybody out there, want a new student, a very good one, a creative one?! Come on!! You earn much!

Ramin replied me back and wrote:

Every program could be considered as an automata which gets a string input and outputs a string output of codes. I think the robustness of algorithms can be interpreted as “redundancy” in this messaging framework. Thus, I recommend this, as an alternative strategy, to bring robustness to computer algorithms from the communications view point.

The idea of translating computer algorithms to dynamical systems is fascinating but first, we should reconsider the “dynamic” properties of our algorithms.

And I wrote him:

You mentioned a very good and interesting point. I wonder if there is a relation between dyamical properties of the system and information content of the message. I guess that the fractal dimension of a trajectory of the system’s output has a relation with output signal’s entropy. Consider this: a stable system converges to a single point in the state space (or output space) (fractal dimension = 0) and the entropy of the output signal converges to the zero as knowing the system is stable is equivalent to knowing what its future would be. A limit cycle leads to a finite fractal dimension (e.g. in 2D state space, it is between 1 and 2), and the entropy of it is finite depending on the length of its descriptor string, and etc.
Properties like robustness may be considered as cross-entropy between source (disturbances) to destination (output signal). hmmm … it is interesting in my mind. Maybe we are reinventing cybernetics!