Suppose that there is a linear problem defined as X = inv(A)b. You solve it using an iterative gradient-descent method defined on some error function like (X – inv(A)b).^2 (or AX-b).^2. Moreover, suppose that you know X is a member of class_X which simplifies the gradient descent method in someway (you know that you should not go in some directions). Can we incorporate this knowledge in traditional linear matrix equalities solvers (not those that are based on calculating the gradient of …) or use it in finding the inverse of A somehow more efficiently? I know that I have not defined this problem clear, but anyway, my descriptions may give some hint on what is the problem: is there any duality relation between calculation of inverse of A and solving the minimization function I mentioned?!
Save Pasargad
We, the undersigned, regretfully have to inform all the inhabitants of our planet earth that one of the greatest parts of the historical heritage of human race is on the verge of permanent extinction. The Islamic Republic of Iran has embarked on the finalizing stages of a dam construction in south of Iran that will ultimately drown the archeological sites of Pasargad and Persepolice, the ancient capital of the Archimedean Empire – a rich and complex site that, since its inception, has been considered by all writers of antiquity as one of the wonders of the ancient world and, thus, a part of the cultural heritage of the human race. Sign this petition here!
My Exhausting Assignment
I have a very exciting assignment for my optimization course: calculate the Hessian matrix for a feedforward neural network. I don’t know if there is any simple trick for simplifying things, but the way I’m extending the usual backpropagation to the second order derivatives are really exhausting. I guess one might have published a paper just for this calculation a few years ago.
(At least, I hope that Bishop’s book has a solution for it. I really don’t want to implement a code without checking it before.)
GNUPlot and Octave
Just now, I’m doing some experiments using gnuplot! It is a cool software IMO! Moreover, I tried Octave and it was cool too. It is somehow (or even more!) like MatLab with the same command lines – as far as I see. It is wonderful that these kinds of softwares are freely available (neglecting the fact that MatLab was also free for me too! 😀 ).
A very interesting phenomenon can be seen in my current life: I am facing a rush of new softwares, tools, and even culture! I guess this learning step is much bigger than whatever I’d in a few last years. Maybe not too! like this condition – at least now.
CSGSA BBQ
Today, we had an annual Computer Science Graduate Student Association (CSGSA) BBQ in Hawrelak park. I’m not that familiar with guys there (and I’m generaly a shy person), so I didn’t participate in all activities there, but overally it was a good program for my Sunday. Well! Hawrelak park is a really beautiful place to walk or run on big fields of grass!
emmm … There, a big dog thought that we would be its owner, and it followed us for a few hundred meters. During that unwanted partnership, it bites a few bikers too and those people thought that it was our own dog!)
Learning LaTeX
Well! Right now, I am learning LaTeX a tutorial and reading some LaTeX files simultaneously. It is a fun experiment, however, I do not like the deadline of the paper which I should prepare using this new word processor.
If LaTeX loves don’t kill me, I must express my doubt in the reason of using such a difficult method for word processing. What’s the problem of using a good written WYSIWYG software? Flexibility?
Intelligence and Your Interface
Many people believe that intelligence is an embodied phenomenon: one cannot be intelligent without having a body to interact with the environment. It is not definable at all.
Moreover, intelligence or looking intelligent (which in someone’s opinion might be the same) needs that all intelligent-looking process of interaction do their job well. If you are able to do many symbolic processing very fast, but you cannot speak at all (or in the way you want) or you understand what you are required to do, you are not considered intelligent by others. I guess in this situation, not only you are not “considered” intelligent, but also you are “not” intelligent at all!
SoloGen is Filtered
My site has been filtered by most Iranian ISPs. It is a bit strange that the government have decided to censor my weblogs (Anti Memoirs (in Farsi) and Thesilog).
Insight into the processes of positive and negative learners
Insight into the processes of ‘positive’ and ‘negative’ learners
… their detailed studies also found a difference in ERNs in “positive” and “negative” learners. The former are people who perform better at choosing the correct response than avoiding the wrong one, and the latter are those who learn better to avoid incorrect responses. The negative learners, they found, showed larger ERNs, suggesting that “these individuals are more affected by, and therefore learn more from, their errors. This notion makes the strong prediction that the feedback negativity should also be relatively larger in these participants to negative compared with positive feedback, which could potentially reflect the neural mechanism causing them to be more sensitive to their mistakes.”
Is there two different paths for avoiding something and selecting something? It seems that there are two different mechanism for processing negative and positive experiences. And it seems that it is (at least) due to reinforcement signal generator.
They explained that “In other words, positive reinforcement learners appear to have experienced greater conflict when choosing between two stimuli that were each previously associated with positive (compared with negative) feedback, whereas negative reinforcement learners may have experienced greater conflict when choosing among negative stimuli.”
(maybe) People do some kind of ordering evaluation instead of mere value comparison for their RL-based decisions. And/Or people have different sensitivity in different region of values, i.e. negative values are stored in coarser details comparing with positive values for some people and vice versa.
Theory of Jokes
Once ago, I became interested in the cognitive mechanism behind jokes. I find these articles about them. Do you have any suggestion on this topic?
Marvin Minsky, JOKES and the Logic of the Cognitive Unconscious, 1980.
Abstract: Freud’s theory of jokes explains how they overcome the mental “censors” that make it hard for us to think “forbidden” thoughts. But his theory did not work so well for humorous nonsense as for other comical subjects. In this essay I argue that the different forms of humor can be seen as much more similar, once we recognize the importance of knowledge about knowledge and, particularly, aspects of thinking concerned with recognizing and suppressing bugs — ineffective or destructive thought processes. When seen in this light, much humor that at first seems pointless, or mysterious, becomes more understandable.
David Chalmers, A Taxonomy of Cognitive Jokes, 1989.
I read it once. I must think more about it and see if our jokes obey the same categorization. However, it is not apparent if it reveals much about the cognitive process of understanding jokes and humors.
Theory of Humor
I don’t know the author of the text. But it may give us some ideas.
Some categorization of jokes. Might be useful to do the same in Farsi.