Connectionists: CfP -- Continual Learning workshop at NIPS 2018

[Razvan Pascanu]

TL;DR: We invite you to our workshop on Continual Learning at this year’s
NIPS. Submission deadline for 4-page abstracts is October 19th.

---------------------

Continual learning (CL) is the ability to learn continually from a stream
of experiential data, building on what was learnt previously, while being
able to reapply, adapt and generalize it to new situations. CL is a
fundamental step towards artificial intelligence, as it allows the learning
agent to continually extend its abilities and adapt them to a continuously
changing environment, a hallmark of natural intelligence. It also has
implications for supervised or unsupervised learning. For example, if a
dataset is not randomly shuffled, or the input distribution shifts over
time, a learned model might overfit to the most recently seen data,
forgetting the rest -- a phenomenon referred to as catastrophic forgetting,
which is a core issue CL systems aim to address.

Continual learning is characterized in practice by a series of desiderata.
A non-complete list of which includes:

   -

   Online learning -- learning occurs at every moment, with no fixed tasks
   or data sets and no clear boundaries between tasks;
   -

   Presence of transfer (forward/backward) -- the learning agent should be
   able to transfer and adapt what it learned from previous experience, data,
   or tasks to new situations, as well as make use of more recent experience
   to improve performance on capabilities learned earlier;
   -

   Resistance to catastrophic forgetting -- new learning should not destroy
   performance on previously seen data;
   -

   Bounded system size -- the agent’s learning capacity should be fixed,
   forcing the system to use its resources intelligently, gracefully
   forgetting what it has learned so as to minimize potential loss of future
   reward;
   -

   No direct access to previous experience -- while the model can remember
   a limited amount of experience, a continual learning algorithm cannot
   assume direct access to all of its past experience or the ability to rewind
   the environment (i.e., t=0 exactly once).

In the first (2016) meeting of this workshop, the focus was on defining a
complete list of desiderata of what a continual learning (CL) enabled
system should be able to do. The focus of the 2018 workshop will be on:

   1.

   how to evaluate CL methods; and
   2.

   how CL compares with related ideas (e.g., life-long learning,
   never-ending learning, transfer learning, meta-learning) and how advances
   in these areas could be useful for continual learning.



In particular, different desiderata of continual learning seem to be in
opposition (e.g., fixed model capacity vs non-catastrophic forgetting vs
the ability to generalize and adapt to new situations), which also raises
the question of what a successful continual learning system should be able
to do. What are the right trade-offs between these different opposing
forces? How do we compare existing algorithms in the face of conflicting
objectives? What metrics are most useful to report? In some cases,
trade-offs will be tightly defined by the way we choose to test the
algorithms. What would be the right benchmarks, datasets or tasks for
productively advancing this topic?

We encourage submission of four-page abstracts describing work in progress
or completed work on topics (1) and (2) above, including work beneficial to
the advancement of CL from related areas, such as:

   -

   Transfer learning
   -

   Multi-task learning
   -

   Meta learning
   -

   Lifelong learning
   -

   Few-shot learning

Finally, we will also encourage presentation of both novel approaches to CL
and implemented systems, which will help concretize the discussion of what
CL is and how to evaluate CL systems.



Confirmed speakers:

   -

   Marc’Aurelio Ranzato (Facebook AI Research)
   -

   John Schulman (OpenAI)
   -

   Raia Hadsell (DeepMind)
   -

   Chelsea Finn (Berkeley & Google Brain)
   -

   Yarin Gal (Oxford)
   -

   Juergen Schmidhuber (IDSIA/NNAISENSE)

Dates:

   -

   Submission deadline: Friday October 19
   -

   Workshop: Friday December 7th

Submission format: 4 page extended abstracts, which can include previously
published work.

More details at the website:
https://sites.google.com/corp/view/continual2018/

Submissions will be managed through EasyChair here:
https://easychair.org/conferences/?conf=cl20180

We look forward to seeing you in December!

Razvan Pascanu, Yee Whye Teh, Mark Ring and Marc Pickett.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20180905/bb9bddf6/attachment.html>