hunch_net hunch_net-2005 hunch_net-2005-29 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: I realized that the tools needed to solve the problem just posted were just created. I tried to sketch out the solution here (also in .lyx and .tex ). It is still quite sketchy (and probably only the few people who understand reductions well can follow). One of the reasons why I started this weblog was to experiment with “research in the open”, and this is an opportunity to do so. Over the next few days, I’ll be filling in details and trying to get things to make sense. If you have additions or ideas, please propose them.
sentIndex sentText sentNum sentScore
1 I realized that the tools needed to solve the problem just posted were just created. [sent-1, score-0.993]
2 I tried to sketch out the solution here (also in . [sent-2, score-0.575]
3 It is still quite sketchy (and probably only the few people who understand reductions well can follow). [sent-5, score-0.938]
4 One of the reasons why I started this weblog was to experiment with “research in the open”, and this is an opportunity to do so. [sent-6, score-0.909]
5 Over the next few days, I’ll be filling in details and trying to get things to make sense. [sent-7, score-0.896]
6 If you have additions or ideas, please propose them. [sent-8, score-0.402]
wordName wordTfidf (topN-words)
[('weblog', 0.299), ('filling', 0.277), ('propose', 0.25), ('sketchy', 0.25), ('realized', 0.24), ('sketch', 0.24), ('posted', 0.231), ('tried', 0.224), ('days', 0.194), ('follow', 0.186), ('needed', 0.183), ('tools', 0.18), ('opportunity', 0.177), ('experiment', 0.169), ('ideas', 0.154), ('please', 0.152), ('started', 0.145), ('reductions', 0.139), ('probably', 0.139), ('details', 0.131), ('trying', 0.128), ('open', 0.127), ('next', 0.127), ('still', 0.123), ('reasons', 0.119), ('ll', 0.118), ('solution', 0.111), ('solve', 0.105), ('understand', 0.1), ('get', 0.089), ('quite', 0.083), ('things', 0.078), ('make', 0.066), ('research', 0.066), ('well', 0.058), ('also', 0.055), ('problem', 0.054), ('people', 0.046), ('one', 0.034)]
simIndex simValue blogId blogTitle
same-blog 1 1.0000001 29 hunch net-2005-02-25-Solution: Reinforcement Learning with Classification
Introduction: I realized that the tools needed to solve the problem just posted were just created. I tried to sketch out the solution here (also in .lyx and .tex ). It is still quite sketchy (and probably only the few people who understand reductions well can follow). One of the reasons why I started this weblog was to experiment with “research in the open”, and this is an opportunity to do so. Over the next few days, I’ll be filling in details and trying to get things to make sense. If you have additions or ideas, please propose them.
2 0.11159392 1 hunch net-2005-01-19-Why I decided to run a weblog.
Introduction: I have decided to run a weblog on machine learning and learning theory research. Here are some reasons: 1) Weblogs enable new functionality: Public comment on papers. No mechanism for this exists at conferences and most journals. I have encountered it once for a science paper. Some communities have mailing lists supporting this, but not machine learning or learning theory. I have often read papers and found myself wishing there was some method to consider other’s questions and read the replies. Conference shortlists. One of the most common conversations at a conference is “what did you find interesting?” There is no explicit mechanism for sharing this information at conferences, and it’s easy to imagine that it would be handy to do so. Evaluation and comment on research directions. Papers are almost exclusively about new research, rather than evaluation (and consideration) of research directions. This last role is satisfied by funding agencies to some extent, but
3 0.10431749 271 hunch net-2007-11-05-CMU wins DARPA Urban Challenge
Introduction: The results have been posted , with CMU first , Stanford second , and Virginia Tech Third . Considering that this was an open event (at least for people in the US), this was a very strong showing for research at universities (instead of defense contractors, for example). Some details should become public at the NIPS workshops . Slashdot has a post with many comments.
4 0.10387145 266 hunch net-2007-10-15-NIPS workshops extended to 3 days
Introduction: (Unofficially, at least.) The Deep Learning Workshop is being held the afternoon before the rest of the workshops in Vancouver, BC. Separate registration is needed, and open. What’s happening fundamentally here is that there are too many interesting workshops to fit into 2 days. Perhaps we can get it officially expanded to 3 days next year.
5 0.095383242 151 hunch net-2006-01-25-1 year
Introduction: At the one year (+5 days) anniversary, the natural question is: “Was it helpful for research?” Answer: Yes, and so it shall continue. Some evidence is provided by noticing that I am about a factor of 2 more overloaded with paper ideas than I’ve ever previously been. It is always hard to estimate counterfactual worlds, but I expect that this is also a factor of 2 more than “What if I had not started the blog?” As for “Why?”, there seem to be two primary effects. A blog is a mechanism for connecting with people who either think like you or are interested in the same problems. This allows for concentration of thinking which is very helpful in solving problems. The process of stating things you don’t understand publicly is very helpful in understanding them. Sometimes you are simply forced to express them in a way which aids understanding. Sometimes someone else says something which helps. And sometimes you discover that someone else has already solved the problem. The
6 0.078858368 305 hunch net-2008-06-30-ICML has a comment system
7 0.076225378 82 hunch net-2005-06-17-Reopening RL->Classification
8 0.074138641 351 hunch net-2009-05-02-Wielding a New Abstraction
9 0.073490918 424 hunch net-2011-02-17-What does Watson mean?
10 0.072247572 96 hunch net-2005-07-21-Six Months
11 0.069651753 22 hunch net-2005-02-18-What it means to do research.
12 0.06887994 49 hunch net-2005-03-30-What can Type Theory teach us about Machine Learning?
13 0.068383135 105 hunch net-2005-08-23-(Dis)similarities between academia and open source programmers
14 0.068094157 458 hunch net-2012-03-06-COLT-ICML Open Questions and ICML Instructions
15 0.067094646 76 hunch net-2005-05-29-Bad ideas
16 0.065670475 454 hunch net-2012-01-30-ICML Posters and Scope
17 0.064623088 297 hunch net-2008-04-22-Taking the next step
18 0.061593529 437 hunch net-2011-07-10-ICML 2011 and the future
19 0.061355442 479 hunch net-2013-01-31-Remote large scale learning class participation
20 0.060799595 142 hunch net-2005-12-22-Yes , I am applying
topicId topicWeight
[(0, 0.127), (1, -0.037), (2, -0.065), (3, 0.055), (4, -0.079), (5, -0.005), (6, 0.077), (7, -0.052), (8, -0.027), (9, 0.025), (10, -0.066), (11, -0.023), (12, -0.024), (13, 0.055), (14, 0.021), (15, -0.014), (16, -0.02), (17, -0.021), (18, -0.063), (19, 0.014), (20, -0.03), (21, 0.069), (22, -0.014), (23, -0.078), (24, 0.056), (25, -0.034), (26, -0.033), (27, -0.015), (28, 0.007), (29, 0.027), (30, 0.169), (31, -0.024), (32, 0.025), (33, 0.005), (34, -0.096), (35, -0.027), (36, 0.09), (37, 0.026), (38, 0.015), (39, 0.046), (40, 0.018), (41, 0.071), (42, 0.007), (43, 0.036), (44, 0.05), (45, 0.023), (46, 0.025), (47, 0.066), (48, 0.014), (49, -0.01)]
simIndex simValue blogId blogTitle
same-blog 1 0.97405541 29 hunch net-2005-02-25-Solution: Reinforcement Learning with Classification
Introduction: I realized that the tools needed to solve the problem just posted were just created. I tried to sketch out the solution here (also in .lyx and .tex ). It is still quite sketchy (and probably only the few people who understand reductions well can follow). One of the reasons why I started this weblog was to experiment with “research in the open”, and this is an opportunity to do so. Over the next few days, I’ll be filling in details and trying to get things to make sense. If you have additions or ideas, please propose them.
2 0.56410468 412 hunch net-2010-09-28-Machined Learnings
Introduction: Paul Mineiro has started Machined Learnings where he’s seriously attempting to do ML research in public. I personally need to read through in greater detail, as much of it is learning reduction related, trying to deal with the sorts of complex source problems that come up in practice.
3 0.54892659 105 hunch net-2005-08-23-(Dis)similarities between academia and open source programmers
Introduction: Martin Pool and I recently discussed the similarities and differences between academia and open source programming. Similarities: Cost profile Research and programming share approximately the same cost profile: A large upfront effort is required to produce something useful, and then “anyone” can use it. (The “anyone” is not quite right for either group because only sufficiently technical people could use it.) Wealth profile A “wealthy” academic or open source programmer is someone who has contributed a lot to other people in research or programs. Much of academia is a “gift culture”: whoever gives the most is most respected. Problems Both academia and open source programming suffer from similar problems. Whether or not (and which) open source program is used are perhaps too-often personality driven rather than driven by capability or usefulness. Similar phenomena can happen in academia with respect to directions of research. Funding is often a problem for
4 0.54745013 231 hunch net-2007-02-10-Best Practices for Collaboration
Introduction: Many people, especially students, haven’t had an opportunity to collaborate with other researchers. Collaboration, especially with remote people can be tricky. Here are some observations of what has worked for me on collaborations involving a few people. Travel and Discuss Almost all collaborations start with in-person discussion. This implies that travel is often necessary. We can hope that in the future we’ll have better systems for starting collaborations remotely (such as blogs), but we aren’t quite there yet. Enable your collaborator . A collaboration can fall apart because one collaborator disables another. This sounds stupid (and it is), but it’s far easier than you might think. Avoid Duplication . Discovering that you and a collaborator have been editing the same thing and now need to waste time reconciling changes is annoying. The best way to avoid this to be explicit about who has write permission to what. Most of the time, a write lock is held for the e
5 0.54704762 82 hunch net-2005-06-17-Reopening RL->Classification
Introduction: In research, it’s often the case that solving a problem helps you realize that it wasn’t the right problem to solve. This is the case for the “ reduce RL to classification ” problem with the solution hinted at here and turned into a paper here . The essential difficulty is that the method of stating and analyzing reductions ends up being nonalgorithmic (unlike previous reductions) unless you work with learning from teleoperated robots as Greg Grudic does. The difficulty here is due to the reduction being dependent on the optimal policy (which a human teleoperator might simulate, but which is otherwise unavailable). So, this problem is “open” again with the caveat that this time we want a more algorithmic solution. Whether or not this is feasible at all is still unclear and evidence in either direction would greatly interest me. A positive answer might have many practical implications in the long run.
6 0.53436023 271 hunch net-2007-11-05-CMU wins DARPA Urban Challenge
7 0.52327001 292 hunch net-2008-03-15-COLT Open Problems
8 0.50517416 294 hunch net-2008-04-12-Blog compromised
9 0.50052953 358 hunch net-2009-06-01-Multitask Poisoning
10 0.48530564 22 hunch net-2005-02-18-What it means to do research.
11 0.47645509 424 hunch net-2011-02-17-What does Watson mean?
12 0.47455826 76 hunch net-2005-05-29-Bad ideas
13 0.46660697 492 hunch net-2013-12-01-NIPS tutorials and Vowpal Wabbit 7.4
14 0.44934976 297 hunch net-2008-04-22-Taking the next step
15 0.44109333 132 hunch net-2005-11-26-The Design of an Optimal Research Environment
16 0.44024533 449 hunch net-2011-11-26-Giving Thanks
17 0.43853441 429 hunch net-2011-04-06-COLT open questions
18 0.43352544 96 hunch net-2005-07-21-Six Months
19 0.4303557 351 hunch net-2009-05-02-Wielding a New Abstraction
20 0.42915753 73 hunch net-2005-05-17-A Short Guide to PhD Graduate Study
topicId topicWeight
[(4, 0.431), (27, 0.148), (53, 0.107), (55, 0.17)]
simIndex simValue blogId blogTitle
1 0.91846609 86 hunch net-2005-06-28-The cross validation problem: cash reward
Introduction: I just presented the cross validation problem at COLT . The problem now has a cash prize (up to $500) associated with it—see the presentation for details. The write-up for colt .
2 0.87139809 88 hunch net-2005-07-01-The Role of Impromptu Talks
Introduction: COLT had an impromptu session which seemed as interesting or more interesting than any other single technical session (despite being only an hour long). There are several roles that an impromptu session can play including: Announcing new work since the paper deadline. Letting this happen now rather than later helps aid the process of research. Discussing a paper that was rejected. Reviewers err sometimes and an impromptu session provides a means to remedy that. Entertainment. We all like to have a bit of fun. For design, the following seem important: Impromptu speakers should not have much time. At COLT, it was 8 minutes, but I have seen even 5 work well. The entire impromptu session should not last too long because the format is dense and promotes restlessness. A half hour or hour can work well. Impromptu talks are a mechanism to let a little bit of chaos into the schedule. They will be chaotic in content, presentation, and usefulness. The fundamental adv
3 0.87046468 108 hunch net-2005-09-06-A link
Introduction: I read through some of the essays of Michael Nielsen today, and recommend them. Principles of Effective Research and Extreme Thinking are both relevant to several discussions here.
same-blog 4 0.8452208 29 hunch net-2005-02-25-Solution: Reinforcement Learning with Classification
Introduction: I realized that the tools needed to solve the problem just posted were just created. I tried to sketch out the solution here (also in .lyx and .tex ). It is still quite sketchy (and probably only the few people who understand reductions well can follow). One of the reasons why I started this weblog was to experiment with “research in the open”, and this is an opportunity to do so. Over the next few days, I’ll be filling in details and trying to get things to make sense. If you have additions or ideas, please propose them.
5 0.76519024 10 hunch net-2005-02-02-Kolmogorov Complexity and Googling
Introduction: Machine learning makes the New Scientist . From the article: COMPUTERS can learn the meaning of words simply by plugging into Google. The finding could bring forward the day that true artificial intelligence is developed‌. But Paul Vitanyi and Rudi Cilibrasi of the National Institute for Mathematics and Computer Science in Amsterdam, the Netherlands, realised that a Google search can be used to measure how closely two words relate to each other. For instance, imagine a computer needs to understand what a hat is. You can read the paper at KC Google . Hat tip: Kolmogorov Mailing List Any thoughts on the paper?
6 0.65985221 129 hunch net-2005-11-07-Prediction Competitions
7 0.63638622 75 hunch net-2005-05-28-Running A Machine Learning Summer School
8 0.48704135 458 hunch net-2012-03-06-COLT-ICML Open Questions and ICML Instructions
9 0.47079867 452 hunch net-2012-01-04-Why ICML? and the summer conferences
10 0.46921521 116 hunch net-2005-09-30-Research in conferences
11 0.46683204 395 hunch net-2010-04-26-Compassionate Reviewing
12 0.46596503 141 hunch net-2005-12-17-Workshops as Franchise Conferences
13 0.46422535 270 hunch net-2007-11-02-The Machine Learning Award goes to …
14 0.45820421 90 hunch net-2005-07-07-The Limits of Learning Theory
15 0.45320994 331 hunch net-2008-12-12-Summer Conferences
16 0.45147279 204 hunch net-2006-08-28-Learning Theory standards for NIPS 2006
17 0.44940615 437 hunch net-2011-07-10-ICML 2011 and the future
18 0.44579995 484 hunch net-2013-06-16-Representative Reviewing
19 0.44514191 40 hunch net-2005-03-13-Avoiding Bad Reviewing
20 0.44258928 151 hunch net-2006-01-25-1 year