hunch_net hunch_net-2013 hunch_net-2013-487 knowledge-graph by maker-knowledge-mining
Source: html
Introduction: A big ouch—all the videos for ICML 2012 were lost in a shuffle. Rajnish sends the below, but if anyone can help that would be greatly appreciated. —————————————————————————— Sincere apologies to ICML community for loosing 2012 archived videos What happened: In order to publish 2013 videos, we decided to move 2012 videos to another server. We have a weekly backup service from the provider but after removing the videos from the current server, when we tried to retrieve the 2012 videos from backup service, the backup did not work because of provider-specific requirements that we had ignored while removing the data from previous server. What are we doing about this: At this point, we are still looking into raw footage to find if we can retrieve some of the videos, but following are the steps we are taking to make sure this does not happen again in future: (1) We are going to create a channel on Vimeo (and potentially on YouTube) and we will publish there the p-in-p- or slide-vers
sentIndex sentText sentNum sentScore
1 A big ouch—all the videos for ICML 2012 were lost in a shuffle. [sent-1, score-0.767]
2 Rajnish sends the below, but if anyone can help that would be greatly appreciated. [sent-2, score-0.189]
3 —————————————————————————— Sincere apologies to ICML community for loosing 2012 archived videos What happened: In order to publish 2013 videos, we decided to move 2012 videos to another server. [sent-3, score-1.76]
4 This will be available by the beginning of Oct 2013. [sent-6, score-0.131]
5 (2) We are going to provide download links from TechTalks so that the slide-version (of p-in-p- version if availbale) of the videos can be directly downloaded by viewers. [sent-7, score-1.173]
6 (3) Of course we are now creating regular backups that do not depend on our service provider. [sent-9, score-0.487]
7 How can you help: If you have downloaded from TechTalks the ICML 2012 videos using external tools, we will really appreciate if you can provide us the videos, please email at support@techtalks. [sent-10, score-1.174]
wordName wordTfidf (topN-words)
[('videos', 0.714), ('service', 0.257), ('backup', 0.238), ('rajnish', 0.193), ('retrieve', 0.193), ('downloaded', 0.171), ('techtalks', 0.171), ('removing', 0.143), ('publish', 0.132), ('apologies', 0.086), ('aug', 0.086), ('youtube', 0.086), ('icml', 0.08), ('depend', 0.079), ('channel', 0.079), ('provider', 0.079), ('sends', 0.079), ('oct', 0.079), ('provide', 0.077), ('thank', 0.075), ('ignored', 0.075), ('available', 0.074), ('going', 0.074), ('regular', 0.071), ('download', 0.071), ('help', 0.069), ('raw', 0.069), ('server', 0.069), ('links', 0.066), ('external', 0.066), ('requirements', 0.066), ('tried', 0.064), ('move', 0.059), ('happened', 0.057), ('beginning', 0.057), ('decided', 0.055), ('steps', 0.055), ('lost', 0.053), ('tools', 0.051), ('appreciate', 0.051), ('email', 0.051), ('potentially', 0.047), ('taking', 0.045), ('looking', 0.044), ('happen', 0.044), ('please', 0.044), ('creating', 0.041), ('greatly', 0.041), ('current', 0.04), ('course', 0.039)]
simIndex simValue blogId blogTitle
same-blog 1 1.0 487 hunch net-2013-07-24-ICML 2012 videos lost
Introduction: A big ouch—all the videos for ICML 2012 were lost in a shuffle. Rajnish sends the below, but if anyone can help that would be greatly appreciated. —————————————————————————— Sincere apologies to ICML community for loosing 2012 archived videos What happened: In order to publish 2013 videos, we decided to move 2012 videos to another server. We have a weekly backup service from the provider but after removing the videos from the current server, when we tried to retrieve the 2012 videos from backup service, the backup did not work because of provider-specific requirements that we had ignored while removing the data from previous server. What are we doing about this: At this point, we are still looking into raw footage to find if we can retrieve some of the videos, but following are the steps we are taking to make sure this does not happen again in future: (1) We are going to create a channel on Vimeo (and potentially on YouTube) and we will publish there the p-in-p- or slide-vers
2 0.22563206 489 hunch net-2013-09-20-No NY ML Symposium in 2013, and some good news
Introduction: There will be no New York ML Symposium this year. The core issue is that NYAS is disorganized by people leaving, pushing back the date, with the current candidate a spring symposium on March 28. Gunnar and I were outvoted here—we were gung ho on organizing a fall symposium, but the rest of the committee wants to wait. In some good news, most of the ICML 2012 videos have been restored from a deep backup.
3 0.2018138 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 0.16184956 479 hunch net-2013-01-31-Remote large scale learning class participation
Introduction: Yann and I have arranged so that people who are interested in our large scale machine learning class and not able to attend in person can follow along via two methods. Videos will be posted with about a 1 day delay on techtalks . This is a side-by-side capture of video+slides from Weyond . We are experimenting with Piazza as a discussion forum. Anyone is welcome to subscribe to Piazza and ask questions there, where I will be monitoring things. update2 : Sign up here . The first lecture is up now, including the revised version of the slides which fixes a few typos and rounds out references.
5 0.090617321 447 hunch net-2011-10-10-ML Symposium and ICML details
Introduction: Everyone should have received notice for NY ML Symposium abstracts. Check carefully, as one was lost by our system. The event itself is October 21, next week. Leon Bottou , Stephen Boyd , and Yoav Freund are giving the invited talks this year, and there are many spotlights on local work spread throughout the day. Chris Wiggins has setup 6(!) ML-interested startups to follow the symposium, which should be of substantial interest to the employment interested. I also wanted to give an update on ICML 2012 . Unlike last year, our deadline is coordinated with AIStat (which is due this Friday). The paper deadline for ICML has been pushed back to February 24 which should allow significant time for finishing up papers after the winter break. Other details may interest people as well: We settled on using CMT after checking out the possibilities. I wasn’t looking for this, because I’ve often found CMT clunky in terms of easy access to the right information. Nevert
6 0.048233528 216 hunch net-2006-11-02-2006 NIPS workshops
7 0.043773081 452 hunch net-2012-01-04-Why ICML? and the summer conferences
8 0.04241851 454 hunch net-2012-01-30-ICML Posters and Scope
9 0.03786613 182 hunch net-2006-06-05-Server Shift, Site Tweaks, Suggestions?
10 0.03772331 403 hunch net-2010-07-18-ICML & COLT 2010
11 0.035867482 29 hunch net-2005-02-25-Solution: Reinforcement Learning with Classification
12 0.035636306 305 hunch net-2008-06-30-ICML has a comment system
13 0.034521818 369 hunch net-2009-08-27-New York Area Machine Learning Events
14 0.034389924 240 hunch net-2007-04-21-Videolectures.net
15 0.033849742 171 hunch net-2006-04-09-Progress in Machine Translation
16 0.033608645 381 hunch net-2009-12-07-Vowpal Wabbit version 4.0, and a NIPS heresy
17 0.032304958 42 hunch net-2005-03-17-Going all the Way, Sometimes
18 0.031234931 134 hunch net-2005-12-01-The Webscience Future
19 0.030178595 117 hunch net-2005-10-03-Not ICML
20 0.030036233 297 hunch net-2008-04-22-Taking the next step
topicId topicWeight
[(0, 0.066), (1, -0.039), (2, -0.021), (3, -0.007), (4, -0.002), (5, 0.011), (6, -0.018), (7, -0.012), (8, -0.038), (9, -0.05), (10, -0.048), (11, -0.017), (12, 0.019), (13, 0.032), (14, 0.048), (15, 0.007), (16, -0.043), (17, -0.041), (18, 0.027), (19, 0.053), (20, 0.06), (21, 0.023), (22, -0.034), (23, -0.005), (24, -0.007), (25, -0.042), (26, -0.1), (27, 0.066), (28, 0.039), (29, -0.002), (30, 0.013), (31, 0.007), (32, -0.024), (33, -0.034), (34, -0.062), (35, -0.039), (36, 0.031), (37, 0.093), (38, -0.026), (39, -0.039), (40, -0.002), (41, 0.067), (42, -0.022), (43, -0.005), (44, 0.084), (45, 0.091), (46, -0.018), (47, -0.013), (48, 0.108), (49, 0.127)]
simIndex simValue blogId blogTitle
same-blog 1 0.97852492 487 hunch net-2013-07-24-ICML 2012 videos lost
Introduction: A big ouch—all the videos for ICML 2012 were lost in a shuffle. Rajnish sends the below, but if anyone can help that would be greatly appreciated. —————————————————————————— Sincere apologies to ICML community for loosing 2012 archived videos What happened: In order to publish 2013 videos, we decided to move 2012 videos to another server. We have a weekly backup service from the provider but after removing the videos from the current server, when we tried to retrieve the 2012 videos from backup service, the backup did not work because of provider-specific requirements that we had ignored while removing the data from previous server. What are we doing about this: At this point, we are still looking into raw footage to find if we can retrieve some of the videos, but following are the steps we are taking to make sure this does not happen again in future: (1) We are going to create a channel on Vimeo (and potentially on YouTube) and we will publish there the p-in-p- or slide-vers
2 0.61404431 489 hunch net-2013-09-20-No NY ML Symposium in 2013, and some good news
Introduction: There will be no New York ML Symposium this year. The core issue is that NYAS is disorganized by people leaving, pushing back the date, with the current candidate a spring symposium on March 28. Gunnar and I were outvoted here—we were gung ho on organizing a fall symposium, but the rest of the committee wants to wait. In some good news, most of the ICML 2012 videos have been restored from a deep backup.
3 0.59463513 479 hunch net-2013-01-31-Remote large scale learning class participation
Introduction: Yann and I have arranged so that people who are interested in our large scale machine learning class and not able to attend in person can follow along via two methods. Videos will be posted with about a 1 day delay on techtalks . This is a side-by-side capture of video+slides from Weyond . We are experimenting with Piazza as a discussion forum. Anyone is welcome to subscribe to Piazza and ask questions there, where I will be monitoring things. update2 : Sign up here . The first lecture is up now, including the revised version of the slides which fixes a few typos and rounds out references.
4 0.56740952 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!
5 0.4754115 447 hunch net-2011-10-10-ML Symposium and ICML details
Introduction: Everyone should have received notice for NY ML Symposium abstracts. Check carefully, as one was lost by our system. The event itself is October 21, next week. Leon Bottou , Stephen Boyd , and Yoav Freund are giving the invited talks this year, and there are many spotlights on local work spread throughout the day. Chris Wiggins has setup 6(!) ML-interested startups to follow the symposium, which should be of substantial interest to the employment interested. I also wanted to give an update on ICML 2012 . Unlike last year, our deadline is coordinated with AIStat (which is due this Friday). The paper deadline for ICML has been pushed back to February 24 which should allow significant time for finishing up papers after the winter break. Other details may interest people as well: We settled on using CMT after checking out the possibilities. I wasn’t looking for this, because I’ve often found CMT clunky in terms of easy access to the right information. Nevert
6 0.45999774 15 hunch net-2005-02-08-Some Links
7 0.40756342 448 hunch net-2011-10-24-2011 ML symposium and the bears
8 0.38664541 494 hunch net-2014-03-11-The New York ML Symposium, take 2
9 0.37734205 340 hunch net-2009-01-28-Nielsen’s talk
10 0.37047157 63 hunch net-2005-04-27-DARPA project: LAGR
11 0.36676913 246 hunch net-2007-06-13-Not Posting
12 0.35559955 240 hunch net-2007-04-21-Videolectures.net
13 0.33311707 176 hunch net-2006-05-01-A conversation between Theo and Pat
14 0.32614401 483 hunch net-2013-06-10-The Large Scale Learning class notes
15 0.32466513 294 hunch net-2008-04-12-Blog compromised
16 0.30190095 354 hunch net-2009-05-17-Server Update
17 0.29511881 231 hunch net-2007-02-10-Best Practices for Collaboration
18 0.29510108 29 hunch net-2005-02-25-Solution: Reinforcement Learning with Classification
19 0.29485849 261 hunch net-2007-08-28-Live ML Class
20 0.29295015 415 hunch net-2010-10-28-NY ML Symposium 2010
topicId topicWeight
[(10, 0.022), (11, 0.5), (27, 0.111), (38, 0.018), (53, 0.048), (55, 0.071), (86, 0.01), (94, 0.079)]
simIndex simValue blogId blogTitle
same-blog 1 0.94860417 487 hunch net-2013-07-24-ICML 2012 videos lost
Introduction: A big ouch—all the videos for ICML 2012 were lost in a shuffle. Rajnish sends the below, but if anyone can help that would be greatly appreciated. —————————————————————————— Sincere apologies to ICML community for loosing 2012 archived videos What happened: In order to publish 2013 videos, we decided to move 2012 videos to another server. We have a weekly backup service from the provider but after removing the videos from the current server, when we tried to retrieve the 2012 videos from backup service, the backup did not work because of provider-specific requirements that we had ignored while removing the data from previous server. What are we doing about this: At this point, we are still looking into raw footage to find if we can retrieve some of the videos, but following are the steps we are taking to make sure this does not happen again in future: (1) We are going to create a channel on Vimeo (and potentially on YouTube) and we will publish there the p-in-p- or slide-vers
2 0.86887521 402 hunch net-2010-07-02-MetaOptimize
Introduction: Joseph Turian creates MetaOptimize for discussion of NLP and ML on big datasets. This includes a blog , but perhaps more importantly a question and answer section . I’m hopeful it will take off.
3 0.78426707 287 hunch net-2008-01-28-Sufficient Computation
Introduction: Do we have computer hardware sufficient for AI? This question is difficult to answer, but here’s a try: One way to achieve AI is by simulating a human brain. A human brain has about 10 15 synapses which operate at about 10 2 per second implying about 10 17 bit ops per second. A modern computer runs at 10 9 cycles/second and operates on 10 2 bits per cycle implying 10 11 bits processed per second. The gap here is only 6 orders of magnitude, which can be plausibly surpassed via cluster machines. For example, the BlueGene/L operates 10 5 nodes (one order of magnitude short). It’s peak recorded performance is about 0.5*10 15 FLOPS which translates to about 10 16 bit ops per second, which is nearly 10 17 . There are many criticisms (both positive and negative) for this argument. Simulation of a human brain might require substantially more detail. Perhaps an additional 10 2 is required per neuron. We may not need to simulate a human brain to achieve AI. Ther
4 0.76154977 265 hunch net-2007-10-14-NIPS workshp: Learning Problem Design
Introduction: Alina and I are organizing a workshop on Learning Problem Design at NIPS . What is learning problem design? It’s about being clever in creating learning problems from otherwise unlabeled data. Read the webpage above for examples. I want to participate! Email us before Nov. 1 with a description of what you want to talk about.
5 0.53913301 264 hunch net-2007-09-30-NIPS workshops are out.
Introduction: Here . I’m particularly interested in the Web Search , Efficient ML , and (of course) Learning Problem Design workshops but there are many others to check out as well. Workshops are a great chance to make progress on or learn about a topic. Relevance and interaction amongst diverse people can sometimes be magical.
6 0.3362875 286 hunch net-2008-01-25-Turing’s Club for Machine Learning
7 0.29922944 221 hunch net-2006-12-04-Structural Problems in NIPS Decision Making
8 0.29615998 96 hunch net-2005-07-21-Six Months
9 0.29573393 437 hunch net-2011-07-10-ICML 2011 and the future
10 0.29540563 95 hunch net-2005-07-14-What Learning Theory might do
11 0.2950232 297 hunch net-2008-04-22-Taking the next step
12 0.29350626 207 hunch net-2006-09-12-Incentive Compatible Reviewing
13 0.29323095 423 hunch net-2011-02-02-User preferences for search engines
14 0.29268083 419 hunch net-2010-12-04-Vowpal Wabbit, version 5.0, and the second heresy
15 0.29201114 454 hunch net-2012-01-30-ICML Posters and Scope
16 0.29170135 253 hunch net-2007-07-06-Idempotent-capable Predictors
17 0.29087609 40 hunch net-2005-03-13-Avoiding Bad Reviewing
18 0.29068324 256 hunch net-2007-07-20-Motivation should be the Responsibility of the Reviewer
19 0.29008973 204 hunch net-2006-08-28-Learning Theory standards for NIPS 2006
20 0.28951403 229 hunch net-2007-01-26-Parallel Machine Learning Problems