Happy New Year!
How is the emergent interaction of the world and your body?!
(an excerpt from a daily dialogue between a believer of embodied behavioral AI to an unknown passenger)
âTo the best of the authorâs knowledge â¦â = âWE WERE TOO LAZY TO DO A REAL LITERATURE SEARCH.â
âResults were found through direct experimentation.â = âWE PLAYED AROUND WITH IT UNTIL IT WORKED.â
âThe data agreed quite well with the predicted model.â = âIF YOU TURN THE PAGE UPSIDE DOWN AND SQUINT, IT DOESNâT LOOK TOO DIFFERENT.â
âIt should be noted that â¦â = âOK, SO MY EXPERIMENTS WERENâT PERFECT. ARE YOU HAPPY NOW??â
âThere results suggest that â¦â = âIF WE TAKE A HUGE LEAP IN REASONING, WE CAN GET MORE MILEAGE OUT OF OUR DATA.â
âFuture work will focus on â¦ â = âYES, WE KNOW THERE IS A BIG FLAW, BUT WE PROMISE WEâLL GET TO IT SOMEDAY.â
ââ¦remains an open question.â = âWE HAVE NO CLUE EITHERâ.
(copied from a comic from www.phdcomics.com, drawn by Jorge Cham if I read it right!)
I looked at the date of BehStrLearning1.doc file which is the first document file of my current paper and it dates back to 7th of September 2004! It means that I am working on this paper for about 4 months! Wow! I wouldnât believe it if I were told that a paper writing might take this much long time. Hopefully, it is in its last parts and I wish(!) it will finish and be submitted very soon.
Iâve 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 â¦ . It means that I do not score schools with symbolic AI approach much. In other words, I score universities which is along my preferences. Iâve 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.
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! Smile! There are a bunch of lovely and good people around the world – friend and stranger- who answer my questions very kindly and helpfully.
Yes! Yes!! It may be exactly you the dear reader whom I am speaking to. Smile! (;
Out there in your lab,
Getting lonely, getting old,
Can you feel me?
Standing in the aisle [of your department!],
With an itchy feet and fading smile
As you have not any good student for a while,
Can you feel me?
Donât help them to bury the strong AI,
Donât give in without a fight!
Out there on your own,
Sitting naked by the phone,
Would you touch me? [It is not necessary to do so physically; it is sufficient to admit me!]
With your sonar against the wall,
Waiting for someone to call out [and implement your SLAM algorithm!]
Would you touch me?
Would you help me to admit to a good Ph.D. program
Open your group, Iâm coming home!
[This is a disappointing part; you must not read it!!!]
[But it was only fantasy
The sonars was too noisy as you can see.
No matter how he try, he could not break free
And the bugs ate into his brain.]
Out there on the road [it refers to your outdoor robot],
Always doing what youâre not told [yes! It needs me to become working],
Can you help me?
Out there beyond the wall,
Breaking bottles in the hall [actually, your mobile robot do so because its obstacle avoidance behavior does not work anymore],
Can you help me?
Donât tell me there is no hope at all.
Together we research, divided we fall!
P.S: The original lyric is from Pink Floyd and I’ve changed it a little!
Hey! Is there anybody out there, want a new student, a very good one, a creative one?! Come on!! You earn much!
A University of Minnesota researcher developed a computational model of addiction which can be used to make predictions about human behavior, animal behavior, and neurophysiology.
Natural increases in dopamine occur after unexpected natural rewards; however, with learning these increases shift from the time of reward delivery to cueing stimuli. In TDRL, once the value function predicts the reward, learning stops. Cocaine and other addictive drugs, however, produce a momentary increase in dopamine through neuropharmacological mechanisms, thereby continuing to drive learning, forcing the brain to over-select choices which lead to getting drugs … (read more)