Connectionists: Lifelong Machine Learning please
Richard Loosemore
rloosemore at susaro.com
Mon Apr 17 17:53:37 EDT 2017
In my opinion a new term IS justified, because one of the premises of
the L2M program at DARPA is that something is not right with current
approaches to the problem of learning in AI systems. They have many
failings, so some radically new thinking is required. That, after all,
is what DARPA is all about: encouraging groundbreaking new ideas.
If your suggestion were adopted, and the "Lifelong Learning Machines"
label were dropped in favor of some variant of one the existing terms,
what would be the point? That would be like saying "The existing
approaches are okay, and we need more of what they are doing." That
seems to me to be exactly the opposite of the intention with the L2M
program.
And, apart from anything else, my own research does directly address the
problem of L2M, but at the same time it does not fit anywhere inside the
existing approaches. Your characterisation of the field in the second
paragraph below is, I am sorry to say, completely irrelevant and almost
meaningless in my own framework.
I don't speak for DARPA, of course. This is just my take on it, and my
interpretation of what was said at the Proposers' Day.
Richard Loosemore
Susaro.
On 4/17/17 3:51 PM, Danny Silver wrote:
>
> Dear Hava and others …
>
>
>
> What is in a name?
>
> Lifelong Learning Machines <= *Lifelong Machine Learning* <= Machine
> Lifelong Learning <= Learning to Learn
>
>
>
> All of the above are concerned with the persistent and cumulative
> nature of learning with machines. They are based on the hypothesis
> that more efficient (shorter training times, fewer training examples)
> and more effective (more accurate hypotheses) learning relies on an
> appropriate inductive bias, one source being prior knowledge from
> related tasks (or examples from the same task domain). They should
> also be concerned with the consolidation of knowledge acquired through
> learning to support inductive bias, which forces one to look at the
> representation of learned knowledge.
>
>
>
> I have been studying *Lifelong Machine Learning* since 1993. The
> field has gone from having no name to several vintages. This is an
> appeal for the community to stay with the title “*Lifelong Machine
> Learning*” unless there is some need to distinquish “Lifelong Learning
> Machines” as a separate discipline.
>
>
>
> In 1995, Rich Caruana and I organized the first NIPS workshop on
> “Learning to Learn: Knowledge Consolidation
> and Transfer in Inductive Systems". See
> http://plato.acadiau.ca/courses/comp/dsilver/NIPS95_LTL/transfer.workshop.1995.html
>
> This workshop produced a seminal book by Sebastian Thrun that
> solidified the title “Learning to Learn” or L2L. See
> http://robots.stanford.edu/papers/thrun.book3.html
>
>
>
> Over the next decade myself and several others started to use the term
> “Machine Lifelong Learning” or ML3.
>
> Our lab created a ML3 contributor website that has fallen behind over
> the years (http://ml3.acadiau.ca/) <http://ml3.acadiau.ca/%29> being
> replaced by material on our current lab website
> http://mlrl.acadiau.ca/ and by ResearchGate websites such as -
> https://www.researchgate.net/profile/Daniel_Silver
>
>
>
> The L2L and ML3 titles lasted well into the first decade of the 2000s
> and was used at the second NIPS workshop on the subject “Inductive
> Transfer : 10 Years Later”. See
> http://socrates.acadiau.ca/courses/comp/dsilver/Share/2005Conf/NIPS2005_ITWS/Website/index.htm
>
>
>
> Along the way Mark Ring has distinquished “Continual Learning” in the
> Reinforcement Learning paradigm as a process of learning ever more
> complicated skills by building on those skills already developed. See
>
> https://www.cs.utexas.edu/~ring/Diss/index.html
> <https://www.cs.utexas.edu/%7Ering/Diss/index.html> and his new
> company http://www.cogitai.com/
>
>
>
> Around about 2010, Eric Eaton and others started to use the term
> “*Lifelong Machine Learning*” or *LML* which many people have come to
> like. Please see Eric’s webpage for some of the work he has been
> involved in https://www.seas.upenn.edu/~eeaton/research.html
> <https://www.seas.upenn.edu/%7Eeeaton/research.html>
>
>
>
> So given that we have the well-used term “*Lifelong Machine Learning*”
> and that the name has changed a few times already, I really do not
> cherish the community moving toward yet another permutation of the
> three words “Lifelong”, “Machine”, and “Leaning”, unless it is really
> a different research area … In which case, I would ask that we use a
> significantly different monicker. I make my case for sticking with
> the title “*Lifelong Machine Learning*” with the list of its uses
> shown below my signature.
>
>
>
> Note that a new research theme is starting to be used that brings
> together machine learning and knowledge representation to solve one of
> the Big AI problems. The problem is how to the learn background
> knowledge so it can be used for reason and the new title is “*Lifelong
> Machine Learning and Reasoning*”.
>
> Recently, I created a ResearchGate project which is gaining followers
>
> https://www.researchgate.net/project/Lifelong-Machine-Learning-and-Reasoning
>
>
>
>
> .. Danny
>
>
>
> ==========================
>
> *Daniel L. Silver *
>
> Professor and Acting Director, Jodrey School of Computer Science
>
> Director, Acadia Institute for Data Analytics
>
> Acadia University,
>
> Office 314, Carnegie Hall,
>
> Wolfville, Nova Scotia Canada B4P 2R6
>
>
>
> t. (902) 585-1413
>
> f. (902) 585-1067
>
>
>
> acadiau.ca <http://www2.acadiau.ca/index.php>
>
> Facebook <https://www.facebook.com/acadiauniversity> Twitter
> <https://twitter.com/acadiau> YouTube
> <https://www.youtube.com/user/AcadiaWebmaster> LinkedIn
> <https://www.linkedin.com/company/acadia-university?trk=biz-companies-cym>
> Flickr <https://www.flickr.com/photos/acadiauniversity/albums>
>
>
>
>
>
> In recent years, there has come to exist a wide variety of websites
> that are currently using “*Lifelong Machine Learning*” including those
> related to:
>
>
>
> Books:
>
> https://www.cs.uic.edu/~liub/lifelong-machine-learning.html
> <https://www.cs.uic.edu/%7Eliub/lifelong-machine-learning.html>
>
>
>
> Papers:
>
> Lifelong machine learning: a paradigm for continuous learning
> <http://link.springer.com/content/pdf/10.1007/s11704-016-6903-6.pdf>
>
> http://www.aaai.org/ocs/index.php/SSS/SSS13/paper/viewFile/5802/5977
>
> http://dl.acm.org/citation.cfm?id=2433459
>
> https://pdfs.semanticscholar.org/fb24/b6917eb42ccbf354371ee9565a3014b51e7c.pdf
>
>
> https://cs.byu.edu/colloquium/sentiment-analysis-and-lifelong-machine-learning
>
>
> https://scholar.google.com/citations?user=Z_vWXgsAAAAJ&hl=en
>
>
>
> Popular Press Articles:
>
> https://www.weforum.org/agenda/2017/01/lifelong-machine-learning/
>
> http://www.rollproject.org/lifelong-machine-learning-systems-optimisation/
>
>
>
>
> Videos:
>
> https://www.youtube.com/watch?v=wc2xn4g1-uU
>
>
>
> Courses:
>
> https://www.cs.uic.edu/~liub/lifelong-learning.html
> <https://www.cs.uic.edu/%7Eliub/lifelong-learning.html>
>
>
>
> Tutorials and Workshops:
>
> https://www.cs.uic.edu/~liub/IJCAI15-tutorial.html
> <https://www.cs.uic.edu/%7Eliub/IJCAI15-tutorial.html>
>
> https://www.seas.upenn.edu/~eeaton/AAAI-SSS13-LML/
> <https://www.seas.upenn.edu/%7Eeeaton/AAAI-SSS13-LML/>
>
> http://repository.ust.hk/ir/Record/1783.1-73755
>
> https://bigdata.cs.dal.ca/news/2014-06-09-000000/seminar-lifelong-machine-learning-and-reasoning
>
>
>
>
> Research Websites:
>
> http://mlrl.acadiau.ca/
>
> https://www.cs.uic.edu/~liub/lifelong-learning.html
> <https://www.cs.uic.edu/%7Eliub/lifelong-learning.html>
>
> https://www.seas.upenn.edu/~eeaton/research.html
> <https://www.seas.upenn.edu/%7Eeeaton/research.html>
>
> https://jaimefernandezdcu.wordpress.com/2016/10/24/lml/
>
>
>
> ++++++++ +++++++++ ++++++++++
>
>
>
> *From: *Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu>
> on behalf of Hava Siegelmann <hava.siegelmann at gmail.com>
> *Date: *Sunday, April 16, 2017 at 1:57 PM
> *To: *"connectionists at mailman.srv.cs.cmu.edu"
> <connectionists at mailman.srv.cs.cmu.edu>
> *Subject: *Re: Connectionists: Lifelong Learning Machines - Call for
> Grants
>
>
>
> Dear Connectionists, it was a typo, Lifelong Learning Machine is NOW
> AVAILABLE - please read, get together and apply.
>
> We have the chance to start a new chapter of AI.
>
>
>
> Hava
>
>
>
>
>
> On Fri, Apr 14, 2017 at 5:41 PM, Hava Siegelmann
> <hava.siegelmann at gmail.com <mailto:hava.siegelmann at gmail.com>> wrote:
>
> Dear Friends
>
>
>
> Lifelong Learning Machines (L2M) call for proposals (or in DARPA
> lingo BAA (Broad agency announcement)) is not available online
> from the DARPA portal
>
>
>
> Note that there is also a link for teaming to enable create small
> groups is you are looking for collaborators.
>
>
>
> Note that DARPA programs are once in a lifetime rather than
> NSF/NIH with repeating ideas. So start reading and prepare your
> applications on time.
>
>
>
>
>
> All the best and much luck -
>
>
>
> Hava Siegelmann
>
>
>
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20170417/cbcce637/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/png
Size: 7485 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20170417/cbcce637/attachment.png>
More information about the Connectionists
mailing list