CAMINO-TRACKVIS 0.2

Thanks to Maxwell Collin's expertise in using nifticlib our new version of CAMINO-TRACKVIS becomes much easier to use. Key features in the new release:

1) One does not need to provide the volume and voxel dimensions.
2) The orientation information needed in Trackvis is automatically read from a NIFTI file so that overlaying FA/MD maps onto the tracts in Trackvis is much smoother without manual editing of the Trackvis header!
3) We also released SOURCE CODE!

Please feel free to share your experiences on the NITRC website so that we can keep improving the tool!

P.S.: Max is really awesome to work with and as promised he made the release possible before my summer travels!!

Emotional bases

People take risks all the time at different levels. When people want to take risks in life especially emotional (non-documentable) risks how can they be calculated? To calculate anything we need a base system. The most popular base system currently for arithmetic is decimal system. Binary system is the most efficacious though!

Given my inclination towards computational perspectives in life and above all my faith in spirituality I think that the most efficacious base system for calculating risks in emotional adventures is {S,B,F}: S-your soul, B-your body, F-your faith. Now as time goes the number of "trits" you use to represent your emotional state keeps increasing (like in a typical decimal/binary system) and everyone's state depends on what kind of arrangement these three values take.

For e.g. One emotional state can be represented as FFSSBFBFS which means that person has his/her faith as the most recent and actually as in numerical systems the highest order values are the left most and in emotional sense the most robust and reliable. For eg. 101 and 102 are similar but 101 and 201 have a large difference. The left most digit plays a huge role.

Now given that to be able to calculate risks involved it is important to start with most reliable and high order values. So always try to begin your adventures before starting to write new emotional states in your life with F,S that way the small fluctuations that happen towards the right side of your emotional state won't matter as much! For e.g. FFSFFFSBFSSBBBB is much more robust (in terms of efficient/stable survival) than BBBSBBFSBSBFFBFFFS. So people who have firm faith in something abstract and are clear in mind about that can try and take risks later on in life and minimize impact as much as possible. That's why cultures try to inculcate faith in children as they grow up. Those left most values value the most and having that perception allows you to calculate or cope with risks involved in emotional adventures.

Depth of a culture

I am notoriously unpopular for my pro-American attitude partly because of my blunt straightforwardness which might be considered extreme. While different people I argue with have different reasons to find faults with American culture some say their culture is not deep and is superficial and materialistic.

See, cultures that are based on or adapt modern science are bound to be like that. In fact the materialism is what separates impulsive judgements from rigor of the reasoning. Sure impulsive judgements might be handy at times but more often than not they are are not dependable with the given size of human population and scale of interaction on the planet.

Older cultures obviously are not based on modern approach to reasoning and tend to associate mysterious depths to understanding of life etc. Thanks to the western influence on the approach of reasoning we have tools to embrace uncertainties in a much better way. Why should we take that embracing uncertainty is a good thing? See, this is based on western influence and western cultures have had to evolve under harsher conditions of life because of climate and landscapes etc. Tropical countries naturally support life without requiring much effort from the human side at least not on the scale needed in colder climates. Well why we do we need to live in harsher climates? Well as I said before the size of human population you know, we can not cram lot of people in one place without dropping the individualistic animal instincts within us. Why do you think western influence resonates with many modulo survival fears!

Embracing uncertainty can seem to be superficial but actually it's deeper on the scale that actually matters for survival. It might seem majority of American export being "service" is superficial but re-think and adjust your views. They know how to run empire at least without repeating mistakes (on a relevant time scale). One can ask why am I so certain about my views. It's mainly because one has to instantiate at a certain level otherwise there won't be any objects of decision and I instantiate (am certain) where there is representation/room for uncertainty.

Obviously America is a big country and I don't have samples of interaction from all of it but from east coast which I believe is the strength of the US in causal terms. Coasts stimulate not just America but most countries on the planet so no big surprise. My experience in the mid-west through Madison also reinforces my hypotheses but I am glad and grateful I experienced east coast first as there are many local optima that can make people get stuck in mid-west type areas.

Steps to install Shogun

Shogun's a huge collection of machine learning tools implemented in C++ and wrapped for MATLAB use. With help of Chris Hinrichs I started using the package for my work in DTI classification. They keep coming up with new version every so often and I needed a lookup place for the set of steps to perform. It is linux based software and it's not as simple as double clicking a setup.exe

So here's the steps assuming you have limited access on the machines:

1. Download the latest release from http://svn.tuebingen.mpg.de/shogun/releases/ (As of today the latest version is 0.9.1)
2. cd download_dir/src
3. ./configure --interfaces=libshogun,libshogunui,matlab --destdir=install_dir --prefix=local -enable-glpk
4. make
5. make install
6. Edit .bash_profile in your $HOME directory to add the following line export LD_LIBRARY_PATH=/lib:install_dirlocal/lib:$LD_LIBRARY_PATH
7. In your MATLAB code: addpath('download_dir/src/matlab')

Look into download_dir/examples for examples.

Happy new year

Today marks the beginning of 2010 and a new 10
Approaching the teen years of 21^st century
Makes me both happy and wary
Happy because we seem to be on the road to recovery
Wary because we can't be complacent too early
For the dynamics of our entropy are too hairy

On a personal level I hope
Everyone can at least glance
At romance
For an awesome blissful trance
That can fuel
One to reach your crowning jewel

The journey of romance
Might not all be rosy
Well what else worthy
Can one get without being risky?

At any rate
Here's the poem I wrote
For a new year
Summarizing my newest experiences in the previous year

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!

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!

CAMINO-TRACKVIS

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.

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.

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.

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.

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.

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.

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!

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!!

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!

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!

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.

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!