hunch_net hunch_net-2007 hunch_net-2007-268 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: The Second Annual Reinforcement Learning Competition is about to get started. The aim of the competition is to facilitate direct comparisons between various learning methods on important and realistic domains. This year’s event will feature well-known benchmark domains as well as more challenging problems of real-world complexity, such as helicopter control and robot soccer keepaway. The competition begins on November 1st, 2007 when training software is released. Results must be submitted by July 1st, 2008. The competition will culminate in an event at ICML-08 in Helsinki, Finland, at which the winners will be announced. For more information, visit the competition website.
sentIndex sentText sentNum sentScore
1 The Second Annual Reinforcement Learning Competition is about to get started. [sent-1, score-0.056]
2 The aim of the competition is to facilitate direct comparisons between various learning methods on important and realistic domains. [sent-2, score-1.6]
3 This year’s event will feature well-known benchmark domains as well as more challenging problems of real-world complexity, such as helicopter control and robot soccer keepaway. [sent-3, score-1.49]
4 The competition begins on November 1st, 2007 when training software is released. [sent-4, score-0.94]
5 The competition will culminate in an event at ICML-08 in Helsinki, Finland, at which the winners will be announced. [sent-6, score-0.949]
6 For more information, visit the competition website. [sent-7, score-0.695]
wordName wordTfidf (topN-words)
[('competition', 0.558), ('event', 0.216), ('helicopter', 0.189), ('soccer', 0.189), ('aim', 0.189), ('november', 0.189), ('winners', 0.175), ('benchmark', 0.175), ('begins', 0.175), ('facilitate', 0.175), ('realistic', 0.175), ('finland', 0.175), ('helsinki', 0.175), ('comparisons', 0.165), ('domains', 0.157), ('robot', 0.151), ('annual', 0.146), ('visit', 0.137), ('challenging', 0.137), ('july', 0.125), ('submitted', 0.125), ('software', 0.122), ('direct', 0.12), ('control', 0.117), ('website', 0.112), ('reinforcement', 0.092), ('training', 0.085), ('feature', 0.081), ('second', 0.074), ('methods', 0.073), ('complexity', 0.073), ('various', 0.069), ('results', 0.064), ('must', 0.059), ('year', 0.057), ('get', 0.056), ('information', 0.055), ('important', 0.054), ('problems', 0.041), ('well', 0.037), ('learning', 0.022)]
simIndex simValue blogId blogTitle
same-blog 1 0.99999976 268 hunch net-2007-10-19-Second Annual Reinforcement Learning Competition
Introduction: The Second Annual Reinforcement Learning Competition is about to get started. The aim of the competition is to facilitate direct comparisons between various learning methods on important and realistic domains. This year’s event will feature well-known benchmark domains as well as more challenging problems of real-world complexity, such as helicopter control and robot soccer keepaway. The competition begins on November 1st, 2007 when training software is released. Results must be submitted by July 1st, 2008. The competition will culminate in an event at ICML-08 in Helsinki, Finland, at which the winners will be announced. For more information, visit the competition website.
2 0.23129165 276 hunch net-2007-12-10-Learning Track of International Planning Competition
Introduction: The International Planning Competition (IPC) is a biennial event organized in the context of the International Conference on Automated Planning and Scheduling (ICAPS). This year, for the first time, there will a learning track of the competition. For more information you can go to the competition web-site . The competitions are typically organized around a number of planning domains that can vary from year to year, where a planning domain is simply a class of problems that share a common action schema—e.g. Blocksworld is a well-known planning domain that contains a problem instance each possible initial tower configuration and goal configuration. Some other domains have included Logistics, Airport, Freecell, PipesWorld, and many others . For each domain the competition includes a number of problems (say 40-50) and the planners are run on each problem with a time limit for each problem (around 30 minutes). The problems are hard enough that many problems are not solved within th
3 0.22381079 283 hunch net-2008-01-07-2008 Summer Machine Learning Conference Schedule
Introduction: Conference Paper due date Conference Date Location AAAI January 22/23/25/30 July 13-17 Chicago, Illinois ICML Feb 8 July 5-9 Helsinki, Finland COLT Feb 20 July 9-12 Helsinki, Finland KDD Feb 23/29 August 24-27 Las Vegas, Nevada UAI Feb 27/Feb 29 July 9-12 Helsinki, Finland Helsinki is a fun place to visit.
4 0.11305062 477 hunch net-2013-01-01-Deep Learning 2012
Introduction: 2012 was a tumultuous year for me, but it was undeniably a great year for deep learning efforts. Signs of this include: Winning a Kaggle competition . Wide adoption of deep learning for speech recognition . Significant industry support . Gains in image recognition . This is a rare event in research: a significant capability breakout. Congratulations are definitely in order for those who managed to achieve it. At this point, deep learning algorithms seem like a choice undeniably worth investigating for real applications with significant data.
5 0.11265998 148 hunch net-2006-01-13-Benchmarks for RL
Introduction: A couple years ago, Drew Bagnell and I started the RLBench project to setup a suite of reinforcement learning benchmark problems. We haven’t been able to touch it (due to lack of time) for a year so the project is on hold. Luckily, there are several other projects such as CLSquare and RL-Glue with a similar goal, and we strongly endorse their continued development. I would like to explain why, especially in the context of criticism of other learning benchmarks. For example, sometimes the UCI Machine Learning Repository is criticized. There are two criticisms I know of: Learning algorithms have overfit to the problems in the repository. It is easy to imagine a mechanism for this happening unintentionally. Strong evidence of this would be provided by learning algorithms which perform great on the UCI machine learning repository but very badly (relative to other learning algorithms) on non-UCI learning problems. I have seen little evidence of this but it remains a po
6 0.10904682 155 hunch net-2006-02-07-Pittsburgh Mind Reading Competition
7 0.088557482 232 hunch net-2007-02-11-24
8 0.087605335 190 hunch net-2006-07-06-Branch Prediction Competition
9 0.086929217 17 hunch net-2005-02-10-Conferences, Dates, Locations
10 0.082678638 197 hunch net-2006-07-17-A Winner
11 0.0789854 446 hunch net-2011-10-03-Monday announcements
12 0.074056685 27 hunch net-2005-02-23-Problem: Reinforcement Learning with Classification
13 0.071888186 390 hunch net-2010-03-12-Netflix Challenge 2 Canceled
14 0.069233023 389 hunch net-2010-02-26-Yahoo! ML events
15 0.062113624 297 hunch net-2008-04-22-Taking the next step
16 0.061098631 336 hunch net-2009-01-19-Netflix prize within epsilon
17 0.058435116 271 hunch net-2007-11-05-CMU wins DARPA Urban Challenge
18 0.058356628 63 hunch net-2005-04-27-DARPA project: LAGR
19 0.056711145 470 hunch net-2012-07-17-MUCMD and BayLearn
20 0.053984985 218 hunch net-2006-11-20-Context and the calculation misperception
topicId topicWeight
[(0, 0.08), (1, -0.016), (2, -0.047), (3, -0.058), (4, 0.008), (5, -0.085), (6, -0.043), (7, 0.007), (8, 0.022), (9, -0.06), (10, -0.058), (11, 0.032), (12, -0.05), (13, -0.009), (14, -0.063), (15, 0.037), (16, 0.034), (17, -0.004), (18, 0.064), (19, 0.086), (20, -0.055), (21, -0.025), (22, -0.054), (23, -0.024), (24, -0.058), (25, 0.084), (26, -0.01), (27, -0.016), (28, -0.084), (29, 0.047), (30, 0.065), (31, 0.058), (32, -0.088), (33, -0.08), (34, -0.168), (35, 0.007), (36, 0.144), (37, 0.056), (38, 0.089), (39, 0.086), (40, -0.06), (41, -0.009), (42, 0.193), (43, -0.037), (44, -0.001), (45, 0.003), (46, 0.048), (47, 0.067), (48, 0.17), (49, 0.073)]
simIndex simValue blogId blogTitle
same-blog 1 0.98194164 268 hunch net-2007-10-19-Second Annual Reinforcement Learning Competition
Introduction: The Second Annual Reinforcement Learning Competition is about to get started. The aim of the competition is to facilitate direct comparisons between various learning methods on important and realistic domains. This year’s event will feature well-known benchmark domains as well as more challenging problems of real-world complexity, such as helicopter control and robot soccer keepaway. The competition begins on November 1st, 2007 when training software is released. Results must be submitted by July 1st, 2008. The competition will culminate in an event at ICML-08 in Helsinki, Finland, at which the winners will be announced. For more information, visit the competition website.
2 0.58848441 276 hunch net-2007-12-10-Learning Track of International Planning Competition
Introduction: The International Planning Competition (IPC) is a biennial event organized in the context of the International Conference on Automated Planning and Scheduling (ICAPS). This year, for the first time, there will a learning track of the competition. For more information you can go to the competition web-site . The competitions are typically organized around a number of planning domains that can vary from year to year, where a planning domain is simply a class of problems that share a common action schema—e.g. Blocksworld is a well-known planning domain that contains a problem instance each possible initial tower configuration and goal configuration. Some other domains have included Logistics, Airport, Freecell, PipesWorld, and many others . For each domain the competition includes a number of problems (say 40-50) and the planners are run on each problem with a time limit for each problem (around 30 minutes). The problems are hard enough that many problems are not solved within th
3 0.52245003 155 hunch net-2006-02-07-Pittsburgh Mind Reading Competition
Introduction: Francisco Pereira points out a fun Prediction Competition . Francisco says: DARPA is sponsoring a competition to analyze data from an unusual functional Magnetic Resonance Imaging experiment. Subjects watch videos inside the scanner while fMRI data are acquired. Unbeknownst to these subjects, the videos have been seen by a panel of other subjects that labeled each instant with labels in categories such as representation (are there tools, body parts, motion, sound), location, presence of actors, emotional content, etc. The challenge is to predict all of these different labels on an instant-by-instant basis from the fMRI data. A few reasons why this is particularly interesting: This is beyond the current state of the art, but not inconceivably hard. This is a new type of experiment design current analysis methods cannot deal with. This is an opportunity to work with a heavily examined and preprocessed neuroimaging dataset. DARPA is offering prizes!
4 0.52012897 283 hunch net-2008-01-07-2008 Summer Machine Learning Conference Schedule
Introduction: Conference Paper due date Conference Date Location AAAI January 22/23/25/30 July 13-17 Chicago, Illinois ICML Feb 8 July 5-9 Helsinki, Finland COLT Feb 20 July 9-12 Helsinki, Finland KDD Feb 23/29 August 24-27 Las Vegas, Nevada UAI Feb 27/Feb 29 July 9-12 Helsinki, Finland Helsinki is a fun place to visit.
5 0.43473855 63 hunch net-2005-04-27-DARPA project: LAGR
Introduction: Larry Jackal has set up the LAGR (“Learning Applied to Ground Robotics”) project (and competition) which seems to be quite well designed. Features include: Many participants (8 going on 12?) Standardized hardware. In the DARPA grand challenge contestants entering with motorcycles are at a severe disadvantage to those entering with a Hummer. Similarly, contestants using more powerful sensors can gain huge advantages. Monthly contests, with full feedback (but since the hardware is standardized, only code is shipped). One of the premises of the program is that robust systems are desired. Monthly evaluations at different locations can help measure this and provide data. Attacks a known hard problem. (cross country driving)
6 0.40508458 190 hunch net-2006-07-06-Branch Prediction Competition
7 0.40139595 372 hunch net-2009-09-29-Machine Learning Protests at the G20
8 0.39265299 336 hunch net-2009-01-19-Netflix prize within epsilon
9 0.37485233 119 hunch net-2005-10-08-We have a winner
10 0.37086982 232 hunch net-2007-02-11-24
11 0.3658779 17 hunch net-2005-02-10-Conferences, Dates, Locations
12 0.36067197 470 hunch net-2012-07-17-MUCMD and BayLearn
13 0.34689295 169 hunch net-2006-04-05-What is state?
14 0.33475175 6 hunch net-2005-01-27-Learning Complete Problems
15 0.33203411 446 hunch net-2011-10-03-Monday announcements
16 0.32139197 66 hunch net-2005-05-03-Conference attendance is mandatory
17 0.31025514 390 hunch net-2010-03-12-Netflix Challenge 2 Canceled
18 0.30957547 389 hunch net-2010-02-26-Yahoo! ML events
19 0.30936879 197 hunch net-2006-07-17-A Winner
20 0.29702294 297 hunch net-2008-04-22-Taking the next step
topicId topicWeight
[(27, 0.097), (53, 0.047), (55, 0.085), (57, 0.62)]
simIndex simValue blogId blogTitle
same-blog 1 0.93875164 268 hunch net-2007-10-19-Second Annual Reinforcement Learning Competition
Introduction: The Second Annual Reinforcement Learning Competition is about to get started. The aim of the competition is to facilitate direct comparisons between various learning methods on important and realistic domains. This year’s event will feature well-known benchmark domains as well as more challenging problems of real-world complexity, such as helicopter control and robot soccer keepaway. The competition begins on November 1st, 2007 when training software is released. Results must be submitted by July 1st, 2008. The competition will culminate in an event at ICML-08 in Helsinki, Finland, at which the winners will be announced. For more information, visit the competition website.
2 0.43825933 461 hunch net-2012-04-09-ICML author feedback is open
Introduction: as of last night, late. When the reviewing deadline passed Wednesday night 15% of reviews were still missing, much higher than I expected. Between late reviews coming in, ACs working overtime through the weekend, and people willing to help in the pinch another ~390 reviews came in, reducing the missing mass to 0.2%. Nailing that last bit and a similar quantity of papers with uniformly low confidence reviews is what remains to be done in terms of basic reviews. We are trying to make all of those happen this week so authors have some chance to respond. I was surprised by the quantity of late reviews, and I think that’s an area where ICML needs to improve in future years. Good reviews are not done in a rush—they are done by setting aside time (like an afternoon), and carefully reading the paper while thinking about implications. Many reviewers do this well but a significant minority aren’t good at scheduling their personal time. In this situation there are several ways to fail:
3 0.2065917 452 hunch net-2012-01-04-Why ICML? and the summer conferences
Introduction: Here’s a quick reference for summer ML-related conferences sorted by due date: Conference Due date Location Reviewing KDD Feb 10 August 12-16, Beijing, China Single Blind COLT Feb 14 June 25-June 27, Edinburgh, Scotland Single Blind? (historically) ICML Feb 24 June 26-July 1, Edinburgh, Scotland Double Blind, author response, zero SPOF UAI March 30 August 15-17, Catalina Islands, California Double Blind, author response Geographically, this is greatly dispersed and the UAI/KDD conflict is unfortunate. Machine Learning conferences are triannual now, between NIPS , AIStat , and ICML . This has not always been the case: the academic default is annual summer conferences, then NIPS started with a December conference, and now AIStat has grown into an April conference. However, the first claim is not quite correct. NIPS and AIStat have few competing venues while ICML implicitly competes with many other conf
4 0.20562106 116 hunch net-2005-09-30-Research in conferences
Introduction: Conferences exist as part of the process of doing research. They provide many roles including “announcing research”, “meeting people”, and “point of reference”. Not all conferences are alike so a basic question is: “to what extent do individual conferences attempt to aid research?” This question is very difficult to answer in any satisfying way. What we can do is compare details of the process across multiple conferences. Comments The average quality of comments across conferences can vary dramatically. At one extreme, the tradition in CS theory conferences is to provide essentially zero feedback. At the other extreme, some conferences have a strong tradition of providing detailed constructive feedback. Detailed feedback can give authors significant guidance about how to improve research. This is the most subjective entry. Blind Virtually all conferences offer single blind review where authors do not know reviewers. Some also provide double blind review where rev
5 0.20205039 395 hunch net-2010-04-26-Compassionate Reviewing
Introduction: Most long conversations between academics seem to converge on the topic of reviewing where almost no one is happy. A basic question is: Should most people be happy? The case against is straightforward. Anyone who watches the flow of papers realizes that most papers amount to little in the longer term. By it’s nature research is brutal, where the second-best method is worthless, and the second person to discover things typically gets no credit. If you think about this for a moment, it’s very different from most other human endeavors. The second best migrant laborer, construction worker, manager, conductor, quarterback, etc… all can manage quite well. If a reviewer has even a vaguely predictive sense of what’s important in the longer term, then most people submitting papers will be unhappy. But this argument unravels, in my experience. Perhaps half of reviews are thoughtless or simply wrong with a small part being simply malicious. And yet, I’m sure that most reviewers genuine
6 0.20093456 270 hunch net-2007-11-02-The Machine Learning Award goes to …
7 0.20012552 437 hunch net-2011-07-10-ICML 2011 and the future
8 0.19966662 484 hunch net-2013-06-16-Representative Reviewing
9 0.19959863 225 hunch net-2007-01-02-Retrospective
10 0.19905892 458 hunch net-2012-03-06-COLT-ICML Open Questions and ICML Instructions
11 0.1981388 89 hunch net-2005-07-04-The Health of COLT
12 0.19709015 40 hunch net-2005-03-13-Avoiding Bad Reviewing
13 0.19615799 454 hunch net-2012-01-30-ICML Posters and Scope
14 0.19502097 466 hunch net-2012-06-05-ICML acceptance statistics
15 0.19403729 90 hunch net-2005-07-07-The Limits of Learning Theory
16 0.19309027 403 hunch net-2010-07-18-ICML & COLT 2010
17 0.19288149 151 hunch net-2006-01-25-1 year
18 0.19264765 149 hunch net-2006-01-18-Is Multitask Learning Black-Boxable?
19 0.19236434 44 hunch net-2005-03-21-Research Styles in Machine Learning
20 0.1922172 77 hunch net-2005-05-29-Maximum Margin Mismatch?