Wednesday, December 30, 2009

Refreshing creativity

I found this post on the math prodigy,Terence Tao's, blog. If not for any of the content just the creativity of using English can get attention and trigger some useful empathy. Creative communication is very refreshing to me!

Monday, December 21, 2009

Consistent performance

I have been in the trance of watching a really great movie, Avatar, since last after noon! See I like Hollywood movies for their outpouring risks that show up as variety and quality! I liked Terminator 1 and 2, True Lies, Titanic and have had great opinion for James Cameron. Now after watching Avatar in 3D IMAX I became a life-long fan of James Cameron. All the movies I mentioned have been a "world wide phenomenon" in movies. There is one other James I really admire: James Horner! The score of A Beautiful Mind has a long lasting impression on me and the score of Avatar is excellent!

See producing something great is great but consistency in it is what really impresses me!

Saturday, December 19, 2009


I have been using CAMINO and TRACKVIS since mid-summer and along the way I built some in-house utilities that I thought should share with DTI researchers. I had written the utilities in C using malloc for memory management but that type of management didn't scale for over million tracts. Then Maxwell Collins suggested to using the "piping management" employed in CAMINO. He then extended and made my code into "releasable format" so in addition to being able to download the utilities package from here, you can also download it from SourceForge and it has been posted to NITRC for review. Below I am pasting the "public description" that I entered while submitting to NITRC.

With increasing efforts on brain connectivity analyses it becomes important to have tools that can allow increased interoperability among different tractography tools. This package allows interoperability between CAMINO and TRACKVIS. CAMINO is a leading software package in DTI processing. The package is from University of College London. TRACKVIS is a tract visualizing utility with capability of visualizing up to and over a million white matter tracts seamlessly. The package is from Massachusetts General Hospital.

The tools in this package allow conversion of tracts from one format to another in a very effective way with ability to handle over a million tracts.

I plan to release some more tools soon.

Military and free market

The two most important (overriding) systemic forces are military and then free market. Free market has some influence on military but the latter overrides in case of a dead lock. There might be (are?) other meta-forces that actually "cause/control" these but these are the objective forces that can be manifested to actually make a difference in the living. It does help to detour (as long as the objective is kept in mind) into some of the spiritualities to have some entanglement effects on the forces but it's hardly replicable or communicable. One has to figure ones own way by honing the empathetical skills which are more or less like theorem proving skills in terms of communicability.

Monday, December 14, 2009

More grease and more

Yesterday I posted a small demo.m. Today I made another small demo.m to convert ROIs in NIFTI format to text files based on a request from my mentor Moo K. Chung, which reminds me also to point to another piece of source code I worked on for Cosine series based representation of white matter tracts.

As I mentioned in my previous post I will soon release CAMINO, TRACKVIS interoperability tools.

Sunday, December 13, 2009

Switching gears

I posted a few times based on my encounters in brain image analysis at the Waisman center. Today I wanted to post a sample demo script on reading output from DTI_TK in MATLAB. Then I realized I will wrap the demo script in a meta post about how important it is to be able to switch gears (if one wants to reduce overhead in interdisciplinary research) not only in terms of conceptualizations but simple things like being able to use multiple platforms and software packages. Since I joined Waisman, I got more comfortable with MAC, LINUX etc. I am no longer just a WINDOWS person although I still cannot trade WINDOWS for any other platform. I plan to release some tools for CAMINO TRACKVIS interoperability as well.

See, all research in interdisciplinary at some level and needs ability to switch gears but applied research just has higher demand (for doing noticeable (even locally) research) on the gears and needs sufficient investments in greasing it properly. I worked on projects in collaboration with Psychology departments before while I was at Temple. I interacted with "psychologists" working on computer vision problems. There the research is aimed at hypothesizing human perception based on Gestalt psychology (and here's the kicker) eventually leading to machines with perception. While working with psychologists in neuroscience like Kim the results should eventually lead to interpretations of human behavior for clinical purposes. Both these objective functions have quite different properties!

Most of my palpable research experience has been in coming up with heuristics motivated by Gestalt principles and apply blackbox methods from simulation based statistics, specifically particle filters for perceptual grouping and robot mapping problems. More lately I have been working with passionate young Assistant Professor,Vikas Singh whose interests are actually in applying and analyzing techniques from optimization theory and machine learning. This is opening up a lot of opportunities for me to actually start think and work on actually analyzing the efficiency/complexity of heuristics. I am seriously hoping to build some skills in "smoothed analysis". Then I need to be able to switch gears from thinking like complexity analyst, to psychologists, to being software engineer (one of my key skill-strengths). Anyways I will blog more specifics on that when I have some real progress in that line. Without further wrapping I will present what I originally intended to present that is a simple demo script to read output from DTI_TK in MATLAB.

You can download the package from here and run demo.m. I am not explaining the details because what I am offering is possible grease into the gear of DTI processing (to save some annoyance) not building the gear. The actual gear itself can be built pretty nicely using the documentation on the DTI_TK website itself.

Monday, November 30, 2009

Estimating empathy

This post has been on the "Set of possible upcoming posts" for over an year now. I have been wanting to write this post since last election campaign. I just had become a big fan of Obama and his stress for inclusive politics to improve the way DC operates the US (and the world :). Then I joined Waisman center whose mission coincidentally focuses on foundations of life, developmental disorders and Neurodegenerative disorders. A few goals essentially are about "understanding" psychological disorders and especially empathy deficits that can produce dysfunctional families!! Obama had mentioned about empathy deficits in Washington while people at Waisman focus more on a social, personal level. Obviously there's empathy involved at many levels of human life.

The main reason I wanted to write about empathy was that although mentions empathy many times in his speeches and which underlies his inclusive attitude, rarely did he say how others can acquire that skill. If you think about it you quickly realize that empathy is the most basic psychological quality (instinct) that creates any value in the society! Think about stock markets, music, movies, any art for that matter, even intelligence, quest for survival etc. So it makes sense to attempt to quantify such an important quality keeping such a scale of human civilization functioning so that there are guidelines for people to try to acquire such ability in an effective way. As Scott always says the meat of non-trivial reasoning is typically in quantifying, since it captures the complexity of the task without taking about trivial (im)possibilities in the rationale-extremes.

So what tools can we rely on! My favorite is obviously computational. As I mentioned before too the notion of computation is really unifying many spheres of knowledge since it tries to model the though process of human beings that underlies every sphere of knowledge. Its impact on all fields is so insuppressibly real that if there is no impact of computer science on a field then its realisticness can be questionable! Studying emotions like empathy and qualities like intelligence are a tricky thing. But as long as we have end goals for these computational thinking can help ask real questions. A few successful examples are the quest for artificial intelligence and computational game theory which ties up computer science and economics which helps design good societal games to keep the society stimulated in a healthy way. Hence for psychologists to ask truly relevant questions about empathy or other types of emotions its important to be able to take the machinist approach.

For e.g. we can rely on tools from interactive proofs (IP) where we can convince others of the truth of the statements using some communication protocols. The IP class is very powerful that means there are lot of things can in theory be communicated with others in effect creating empathy. Of course finding the protocols itself might be exponentially hard based on what we want to communicate. Usually experience in survival (survival instinct) seems to be the closest causal reason for intelligence which can be efficiently verified (polynomial time verifiability). Isomorphisms across spheres of knowledge and across time actually indicates that and actually realizing those isomorphisms actually fascinates me and indicates robustness of our human survival instincts.

The key to pick on survival instinct as the cause is the assumption (axiom) that everyone wants to survive. But how do you communicate with those who don't view this axiom like suicide bombers etc.? Well that's why we need some sort of enforcement of axioms otherwise there can be no basis for reasoning. Usually the best way to enforce axioms is to show the benefits of having those axioms like let's say proving non-trivial theorems (consequences) of those axioms and hoping that at least one of the consequences impresses them to fall for the axioms. For e.g. people fall for America for various reasons, like money, liberty, luxuries etc. etc. Empathy can only be verified after achieving it. Actual way of achieving is like coming up with theorems. So estimation of empathy is equivalent to theorem proving which means it's NP-hard! We can only hope to achieve practical approximations assuming P!=NP.

Wednesday, October 14, 2009

Computer Science in Neuroscience

I got a job basically through a fellowship which wanted to bring in graduates in Computer Science to look at biological problems. For the past 9 months I have been looking at brain image data especially Diffusion Tensor Data trying to do basic processing and also applying classification methods and developing segmentation methods with several collaborators. Because of the channel I was hired through and because of the circle I am spending my working (and social) hours I can clearly see how Neuroscience (and biology in general) can drastically benefit from CS wisdom. It's an intriguing thing that our quest for machines laid the foundation to understand their language which in turn gave a fresh perspective for the foundation of modern science that in turn can help define our understanding of life.

CS wisdom can affect research pace in neuroscience on many many different levels. Just by applying software engineering skills you can grease a lot of processing. Machine learning/data mining/Artificial Intelligence methods can obviously help making sense of the biological sensor data. CS wisdom can help apply blackbox type research style to start making progress. This wisdom is almost always the fundamental tool in complexity theory: we need to start somewhere for the general problem setting and then dig deeper to exploit specific instances of problems as needed. One thing I noticed is that lack of such perspective can hold back lot of progress. Also another wisdom you can get from CS scientists like Umesh Vazirani is to focus on higher order bits. Well as I mentioned in my previous post building bridges for wisdom between CS and Neuroscience is allowing me some good times.

Monday, September 28, 2009

Building bridges

We all want to work in a way we like and these likes evolve over time based on amount of success (positive feedback) one has in it. Typically in an academic career path one has to build either a combination of consulting + research or teaching + research. Teaching + research is a bit harder path and typically requires shiny background like top schools top thesis etc. Consulting + research is more viable for average PhDs (like mine) and not so ivory background. Good thing is transitioning between the two is possible thanks to interdisciplinary and more importantly applied research. It's always nicer to be able to communicate between seemingly unrelated groups of research as it can save lots of redundant efforts. Having strong bridges between spheres of our knowledge makes the knowledge base only stronger. There is lot of opportunity currently in building bridges in research which in my opinion is another crowning impact of Computer Science in terms of actual machines, software and most importantly complexity theory.

Saturday, September 26, 2009

Streaks of thought: Streak 26

A while ago I had a post on human rights and money. The point kind of was that our progress can be measured by our affordability of human rights. Well why do we call that progress? It's because it gives more chances to people to spring back from honest mistakes. There might be some abusers of the progress but usually those can be caught. This is because giving second chances to people is inherently rooted in wanting second chances for oneself! It all has to do with estimating empathy in lives. I have been procrastinating to write a post about it. Hopefully I will finish it sometime this year!

Wednesday, September 16, 2009

Animal analysis

For past two nights I was watching Animal Planet before going to bed (to avoid repeats on CNN). One night I saw "Monsters Inside Me" which showed the dangers of parasites lurking around us. The wilder the environment gets the more danger we run into. The show reminded how our "civilization (= rights + responsibilities)" process was not just for sympathy, empathy in the high-functioning sense but essentially a Darwinian process. We had to cluster around to separate other killers and the purpose of clustering is defeated without civilization because we would kill among ourselves. We still do but we came a long way.

Yesterday I watched "Killing for Living" which showed how in many species many babies are born-murderers and kill their siblings and in some cases parents kill their children etc. for food. Males kill each other and get killed by females for mating etc. The show said "Just because you are their kind doesn't mean they won't kill you!" One particular instance was striking: Typically stags fight almost to death for mating with female deers but one specific sub-species just have an "abstract fight" where they decide who the winner is without touching each other just by making abstract fight moves!! That is an instance of using brain more than bran! We probably evolved from such sub-species of apes who loved being alive more than sex and reproduction! This probably was the first instance of questioning the instincts! Of course now questioning is one of the seed pillars of our civilization!

Sometimes when things in our high-functioning world relationships (both professional and personal) are frustrating such animal knowledge can give good perspectives on how better off we are in the race of evolution. Killings in today's societies are still very marginal (except for extreme cases like Darfur etc. where the population is still behind in civilization) and most of us get food and get to mate without getting killed!!

Sunday, September 13, 2009

Streaks of thought: Streak 25

CNN is a great way to get political news! Being liberal I tried MSNBC and did not like the certainty pitch. I didn't even bother to try Fox not for their rightwingness but because I assumed their certainty! I like CNN's certainty in uncertainty. Watching news gives me some nice streaks for my blog: American democracy is strong because it has strong middle class. But what does it take for a society to have a strong middle class. As a gross oversimplification I had a streak saying that we need people with balls. Then a strong sense of entitlement and a pinch of empathy (added with lot of perspiration to enforce, of course) can produce both world class rich people and constantly strong middle class!

Monday, August 31, 2009

Vacation by choice

August 2009 has been a great month in many aspects which kind of means lesser posts on my blog as well. More or less after graduating it's been harder to wander in meta space of analyzing life since I am actually living the life!

For the first time in my life every I had a vacation by choice/ Although I managed to sneak in a few hours of meetings this has been a great vacation with my friend Amy! I have taken time off from work a few times before but it's mostly been very situational and for others and not really by choice for the vacation sake! After a wonderful weekend trip to Niagara falls (trying hard not to get trapped on the Canadian side) we spent the week just in the wonder of taking a vacation!

In creating value I realized the concept of affording (not just financially) vacation is a good indicator of measuring the success! Even religions also encourage this idea by concepts like keeping sabbath etc. It's just probably trivial to acknowledge that relaxing for relaxing sake is a good idea to being balanced ensuring long-term productivity. But actually experiencing that is not so trivial experience especially for someone growing up in a lower middle class in a third world country. The fact that such experiences are possible is a good way to keep human efforts for progress stimulated!

Saturday, July 25, 2009

Affording half-knowledge

I wanted to write this post in late September 2007 when I was still figuring out how to create enough value for my work in computer vision and robotics that would be worth an average PhD from CIS department at Temple University. Growing up in a country not only with low resource/population ratio and system's quite immature (relative to US standards: look we need some standards and I prefer US standards!) it was a common thing to hear "Half-knowledge is dangerous". Such perspectives are so deeply rooted in the culture that risk taking is almost impossible (probabilistically people who take risk is roughly 0.000001=1/Million).

Risk for potential embarrassment and failure is a necessity for growth! This assumption was revived after watch season 1.4 of The Universe which inspired me to finish this post. One episode on "Beyond Big Bang" was really appealing as it showed the journey of humans' theorizing about the universe. History channel put together these events nicely in perspective of how the current established theory (still of course incomplete) about universe is an outcome of so many attempts which were either only partially correct or wrong. So essentially we all survived through "half-knowledge" phases and still do not have complete knowledge about anything. There are dangers in having half-knowledge but this is a necessary transitional stage to attaining full-knowledge as it is continuous process. So it always essential to be able to afford half-knowledge.

To afford half-knowledge we need to create value which is a very important part of the survival business. Creating value obviously needs forward filtering and backward smoothing by developing models, gathering observations and evaluating them by communicating with the rest of the human community. The key point I want to make though is that we need to start with some model, some proposal distribution, some importance weighting scheme so that we can eventually get it right. The point is there's is no point in waiting for ever to get it all right since that would mean not being able to afford half-knowledge. Scientists or systems that can afford half-knowledge are analogous "bullet-swallowers" unlike "bullet-dodgers". So questions like: When are you ready to graduate? When is a romantic relationship good enough for marriage? How much money do I need to open a company? When do you sell a product? etc. all can be answered only if we can "swallow" and create value to be able to afford half-knowledge.

Friday, July 17, 2009

Reasoning reason

We all crave to know reasons to different levels. The pathway to peace is having control over that craving as well. We need to have a balance (as always) between

1) actually discovering reasons that can be "objectively communicated" for better lives and
2) bettering our lives by knowing the limits of objective communication and letting go.

The level of detail of reasoning we would be aware of is influenced by the amount of survival stake in knowing the level. The more we grow in number (population) the more detailed of a level we would need. Also there are many equivalences among different types of reasoning like for e.g. there are many "equivalence" theorems and laws in our knowledge base. This is another reason you should reason yourself not to reason every thing in your life.

Reasoning with people in relationships is pretty hard mainly because of assumption-mismatches. There are two ways out:

1) Either try to control the craving to reason everything or
2) Try to have relationships with people from different cultures where you can comfort yourself because assumption-mismatches can be justified to be more valid easily!

Tuesday, June 30, 2009

Old website on a new server

I no longer can host my website on Temple so I moved it to Waisman's hosting server here! I hope to redesign and update my website sometime.

Sunday, June 28, 2009

Track record

Coming from a not-stellar undergrad college I not only got a chance to have a closer look at the value of "track record" in academia and life. Thanks to transition to America I also got to see how system designs can make a difference not only in realizing ones own potential but in essentially defining potentials of human beings.

Lately I have been looking at an inverse problem of learning classifiers for autism using DTI. Not being primarily a machine-learning researcher I focus on an "feature-selection" process for achieving better classification accuracies. Thanks to Chris Hinrichs' help and amazingly useful implementations of Support Vector Machines, I am now able to use these tools to play around verifying the power of different features. It's generally known that any generic computational learning problem is usually infeasible whether using Monte-Carlo methods or using deterministic methods. Feature selection is a very important problem in itself that demands exploitation of structures of the problem at hand. Just this morning I had a nice experience of using a priori information in extracting the features from the DTI data for the autism study and was able to get 100% classification accuracy using leave-one-out cross validation. The features were extracted by Nick Lange using statistical tests and more importantly using biological prior. Statistical tests are usually only a verification step.

Now why all the feature selection mumbo-jumbo for the post titled "Track record". Well, recently Scott posted on his blog about "two-conference solution" for better feature selection in theory community using Innovations in Computer Science (ICS). See, besides which schools you have graduated from, these conferences, journals are fundamentally involved in feature selection process for either a binary classification (good researchers vs. bad researchers) or multi-class problem (exceptional, average, survivalist, bad etc.). Every field has these coveted conferences (like SODA/FOCS/STOC for theoretical computer science, ICCV/CVPR for computer vision, IROS/RSS for robotics) people die-hard to publish in. Even though publishing and bringing in grant money and good feedback in teaching etc. all form huge part of track record for a tenure track publications are the most important and independent dimension necessary for discriminative analysis. There is always a need to balance between "false positives" and "false negatives" in any learning problem in addition to taking care of "outliers/wrong labels".

Since it's hard to change the influence of publications (or find another as uncorrelated feature) on a track record it's important that we try to keep the data in that feature as independent and unbiased as possible. For that there have to be "checks and balances" between types of efforts encouraged in research. This might involve creating new venues for newly discovered efforts. Thanks to worlds most individualistic and worlds biggest democratic society America tends to find such balances in time most of the time (even in establishing track records) and that's what keeps doors open for the underprivileged while banning imposters!

Saturday, June 27, 2009

Can traveling be revealing?

My life for the past few months has involved lot of traveling. I heard on TV sometime that traveling to places can be "revealing" and that you get time to introspect your life and find what's most dear to you etc. Well it seems to hold true best when traveling to new and unfamiliar places can give stimulate the urge of introspection. If it's more about traveling to known places and meeting already known people it becomes more of nostalgic and less of revealing.

The most revealing place was watching variety of animals (many for the first time) in the Madison zoo! Different animals were doing different things in their containments. It was amazing to see chimps giving facial expressions ridiculously close to ours and then cute rodent family animals. By watching other animals we realize our most basic assumptions of what we do in our lives rely on simply that "we just evolved to create". Creationism seems to have helped our species much more than anything else in terms of dominating the planet. We create stuff ranging from materialistic things (like food, tools) to objective abstract concepts (like math, science) to subject abstract concepts (religion, spirituality, love). In my opinion "discovery" is only a by-product of our basic creationism. We get bored and loose purpose in life if we don't feel we are creating something. To me it precedes even peace!

Thursday, May 21, 2009

Streaks of thought: Streak 24

Credit is obtained using communication. Systemic credit is maintained using interpretations while karmic credit is maintained using intentions, above the limits of language! Karmic credit is superset of systemic credit: every result in system can be justified by karma but not vice versa.

Well at least that's what we like to tell ourselves until we have better communication capabilities :)

Saturday, April 11, 2009


A while ago I had a post reminding that heart-breaks have more to do with brain than with heart. My blog has a theme of meta-analysis of living. I recently started working on brain image analysis thanks to the inter-disciplinary thrust in academia that permits researchers like me to survive. After baffling with the basic problems of data process pipelining for about 2 months the data has been slowly growing on me (as with pretty much anything in my life: besides my very basic curiosity instincts and love for brilliance, everything else has grown on me starting in about 1-2 months :)

Psychological analysis until the advent of brain image acquisition and computational learning has mostly been non-rigorous and often can lead to faulty conclusions. For example: "guys can do a lot for a girl merely by evolutionary instincts but in olden days when knowledge about biology and psychology was limited when we don't understand it fully we can conclude things like females are witches they can take control of men etc. etc. That's what made people in ancient days conclude such things. " Such psychological analyses also can lead to creating characters like confessor in Legend of the Seeker series. They are so attractive that the opposite person if confessed becomes an obedient slave!

The psychology people look at behavioral data and try to perform some statistical tests (typically t-test) to see if null-hypothesis can be rejected. The main problem with behavioral data is that usually conclusions would be "trivial" or very questionable if they are non-trivial! Ability to look inside the brain and work on that data can (to some extent) alleviate such problems because in some sense we are looking at the data more close to the "causal" processes of the behavior.

For the past two-months I have been looking at an dataset. At first I had hard time understanding autism but then I realized the effort to understand some out of the norm behaviors is rewarding in itself as it can help us build tolerance and de-couple the actual person (soul?) with his behavior. For the past few weeks I have been seeing lot of "brain related" news on the media: Natasha Richardson's death, Michael J. Fox's appearance on talk shows, Jim Carrey's support for autism etc. etc. I guess when you are working on something and you have access to the world you will filter the information through your own lens :)

Brain image analysis is a one of the very important inverse problems as it can not only have many many applications relevant for day to day life but also give insights into the origins of our life the answer to which can satisfy every single soul on this planet! I never saw a real brain so far (I might soon) but one of my colleagues here saw human, rat and dog brains and she tells me that rat and dog brains are much flatter than ours. It makes me wonder if our never ending self-referential questioning might have created those "folds"! Well we don't know if our questioning is from folds or we form folds because of our questioning instinct. But something interesting can be observed in children's behavior. In general a child is much more curious and can learn faster than the adult counterpart. I think this is because a child is inherently more vulnerable. than an adult and he craves for knowledge and information that can help him survive. Since our bodies are not "wild" compared to other animals we needed to fold up our brain a lot to be able to exist so long on this planet! And so far it seems to pay off to focus on brain. So roll up your sleeves and tone up those folds by working out on relevant hard problems! By analyzing brain data I hope I am doing it :)

Monday, March 30, 2009

Communicative ads

Lately because of watching CNN I ran into two appealing advertisements which I am embedding below. Different ads appeal to different people. I like inspirational and inclusive ads with good music.

I met many American undergrads here in Madison who major in journalism, communications and some of them want to direct ads. Creating excellent ads is a very very creative job! Any skill eventually gets recognized only when communicated in some way or another, for almost trivial reasons. The better the communication skills the sooner you can further you can your career. American products, research, service etc. all usually lead the world because of both good communication and content. BTW it does not pay to just learn the superficial presentation skills. In fact a good communication actually involves real underlying content!

Saturday, March 28, 2009

Earth hour

I have been posting a few times with environment awareness this year. Today evening 8:30PM local time is a call for a world-wide symbolic event about earth consciousness where people involved turn off all unessential lighting for an hour. A similar type of event happens more on a regular basis (third Sunday of every month) for world peace through their meditative perspectives.

Without getting too much into what's essential and what's not to pick on this event just think about adding "earth factor" in your life in general. See people always make decisions by using many variables like money, subjective satisfaction, long-term (conceivable) benefit, short-term reliefs etc. Just add one more to that list. It's not that hard actually. For e.g. limit hot water usage, don't use straws, lids when you are not drinking while moving, check the size of napkins before using them (tear them into two if they are too big, for reuse), volunteer at your house by separating trash from recyclable stuff (win at home before winning outside) etc. etc. Your brain becomes a bit sharper too!

I had started liking actor Edward Norton since his performance in Illusionist (actually knew about him since only then :) Recently I saw him on Larry King live where I learnt he is an activist for earth consciousness related stuff. My admiration of him grew very much. When he said he does not own a car and drives only hybrids when he rents one, I was totally flat and actually felt proud because I have been successful so far in not buying a car even when some of my friends suggested me to buy one in since I have a "job" and the car market's kind of favorable for buying!

Stand as an example in your local neighborhoods of influence and slowly it can become global process. One thing I learnt that helps is not to preach. Just do it if you believe in it. Time will select those who pass the tests anyways.

Wednesday, March 25, 2009

Versing in inverses

Inverse problems form a central part for researchers in pattern analysis and machine intelligence. Data is assumed to be generated by an "underlying process" linear or non-linear and the goal is to "understand" the process. By understanding here I mean having an increased control on the predictability of the data. There are two main top-level categories of processes that effect the data we observe: (1) The true/hidden process and (2) the data acquisition process. The actual goal is to understand (1). The more we account for (2) explicitly the better versed we can be in the real inverse problem of understanding (1).

I have worked on contour grouping and robot mapping problems where the goal was to use 2D spatial data and range data respectively for recognition and navigation applications. In computer vision and robotics main stream pretty much focuses on inferring the computers very specific abilities of humans like recognition and navigation without worrying the true underlying process that generates recognition and navigation abilities. It's like relaxing the problem of predictability to constrained replicability using the observed data without all the way going back to the process that generated the original data. I should mention some people are working in that direction.

Lately I have been working on brain image data. Besides using 3D spatial data there is quite an effort to reach closer to the original process that still has a lot of fertility in terms of academic careers. Since brain imaging has medical implications the conclusions/applications tend to be conservative and hence the goal becomes to get to the real process as closely as possible before we generate new applications from observed data. To put it in different words, it's a very conservative data mining AI application. Yesterday I met Daniel Rowe who was all advertising about his grand unified theory (GUT) about fMRI data processing to account for (2) as much as possible in a unified way. This is very useful as it allows us to get closer to the real (1).

Life is a very interesting process too that generates lots of data in Nature. Understanding life is a very hard inverse problem. We need as much data as possible to be able to confidently understand non-trivial facts about life. Hence the basic assumption of life is to sustain it as long as we can and for that we need to make it valuable and interesting without influencing independent will too much that can reduce the utility of the data. Many generations have been trying to understand the process using contemporary analytical tools. In some sense its hardness is what actually makes it interesting, as I kind of discussed about it before.

I thought about writing about this about 6 months ago. Finally almost as a total random event, I just decided to write it up tonight! It's hard to completely explain the underlying process of my thoughts :) A key problem in data analysis is scale. I would like to post about it sometime but for a nice discussion about this problem in the context of computer vision, look at this paper by Song-Chun Zhu whose work I really admire.

Wednesday, March 04, 2009

Is 200 years long enough?

Thanks to my roommates' TV I watch news these days more regularly and also today started to use the "TeVo" feature to record British Prime Minister, Gordon Browns' address to the joint congress session in Washington. I saw the first few minutes and he was all praising US for it's leadership for the past 200 years and all. I hope to watch the rest later (if my TeVo recording trial works).

When people praise America for its greatness and leadership that it has shown so far, the nay sayers tell that 200 years is not that of a long time. My argument is that 200 years is really a long time given the strides of changes we have seen in the past two centuries. In my opinion a lot more recordable and impacting things happened recently. Science has seen tremendous progress mainly because of its impact on our survival abilities. We are more globally connected than ever before. And besides that all these things happened very fast. When the Great Depression that happened in 30s the world was a different place than what it is now. If the economy goes down in one major country then the rest of the world kind of goes down with it and vice versa. Word Wars brought a lot of changes in the world but at a cost of lot of lives. This economic crisis is better than those wars because atleast we are not paying lives. I have strong faith in resilience of the human civilization.

Infact you know I see this crisis as a kind of progress in our civilization because instead of needing "deadly-life-threatening" crisis to become better at survival we just need a "deadly-economy-threatening" crisis to make a new stride in terms of improved survival like becoming more aware of the climate in terms of reusing, recyling and optimizing energy usage etc., becoming more aware that peace and security are more feasible by better means (like giving hope and opportunities) than just killing etc.

It's not the absolute number of years that matters it how much we got done during those years that matters if those years are long enough. So yeah I think the leadership shown by US in the past 200 years is not just beginners luck or random chance but an outcome of a strife towards achieving a principled approach in dealing with human civilization.

Saturday, February 14, 2009

Streaks of thought: Streak 23

People whose lives revolve around issues way beyond survival are the ones who often need justifications which undeniably rely on the faith in survival. That's probably one of the reasons life is valued much more (in terms of investing money for a system) in US compared to other poorer countries.

An instance as simple as deciding to board a roller-coaster at Six-flags can highlight the importance of faith: Do we check for each nut and bolt of the machine we are boarding? Do we know for sure if everything is safe? It's just the faith in the system that if something goes wrong things will be "justified" appropriately by the system. Since human made systems cannot be perfect we ultimately tend to show faith in karmic system.

Have faith, fun and a happy Valentine's day whether you have a Valentine or don't.

Tuesday, February 03, 2009

Human rights and money

Recently I had to take a few courses on issues involved in researching human data. There I got to see some of the basic assumptions (beliefs) guiding the system design to protect human rights. An e.g. is: "Respect for Persons incorporates at least two ethical convictions: first, that individuals should be treated as autonomous agents, and second, that persons with diminished autonomy are entitled to protection."

The ability in sustaining, enforcing and evolving such basic assumptions are a measure of development of a society or system. Only a handful of countries in the world have measurable development. What I mean is that for example in the assumption in above there needs to be clear quantifiable measure of autonomy or amount of protection etc. There's some level of such analysis based on money in US. I heard from one of my previous colleagues that for e.g. a law enforcement should not cost more than a million dollars per life or something like that.

Without human rights all the fight in making money for life is useless. Money and human rights advocation have to be grown on par because of the mutual-dependency for any sort-of real value of either of them. After all what's the use of money if we don't spend it! Spending on human rights is a smart investment because it motivates human life perpetuation: a self-justified anthropic reason:)

Friday, January 23, 2009


Recylemania is a way to motivate those who have a "need to be rewarded immediately" to care about the environment. Well it's how societies are designed anyways. Top 1% of the population has the global perspective for long-term benefits and they design (at least ought to) the structure for the rest 99%.

I hope I get to see even more of such things starting this year! I am proud to be part of Temple :)

Wednesday, January 21, 2009

Inauguration of power

I missed watching Obama's inauguration live but did watch it yesterday night and boy can we ever not learn something new from him! He is as focussed and empathetic and energetic and enabling as ever. I have always been thinking of America in a way which he beautifully orates but listening from him renews our timeless creed in hope, faith and hence dignity of life. His inauguration of power surely will help harness inner most powers of millions to maximize sustainable life on this planet.

Thursday, January 01, 2009

Video wishes for 2009

With my recently discovered ability to add music to making videos I decided to convert my textual greetings into a visual one!