<div dir="ltr"><p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">===============================================</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Compact Deep Neural Network Representation with Industrial
Applications</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">NIPS 2018 Workshop</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Friday, December 7, 2018</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Palais des Congrès de Montréal, Montréal, Canada</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">================================================ </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">This workshop aims to bring together researchers, educators,
practitioners who are interested in techniques as well as applications of
making compact and efficient neural network representations. One main theme of
the workshop discussion is to build up consensus in this rapidly developed
field, and in particular, to establish close connection between researchers in
machine learning community and engineers in industry. We believe the workshop is beneficial to both
academic researchers as well as industrial practitioners. </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">News: </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">. the workshop NIPS webpage:
<a href="https://nips.cc/Conferences/2018/Schedule?showEvent=10941">https://nips.cc/Conferences/2018/Schedule?showEvent=10941</a></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">. the workshop html webpage is online at
<a href="https://lixinfan01.wixsite.com/cdnnria">https://lixinfan01.wixsite.com/cdnnria</a></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">. the workshop OpenReview submission site is online at </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"><a href="https://openreview.net/group?id=NIPS.cc/2018/Workshop/CDNNRIA">https://openreview.net/group?id=NIPS.cc/2018/Workshop/CDNNRIA</a></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">. Notice: the workshop submission deadline is changed to 20
Oct 2018 (see below) ! </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">. We will help authors of accepted submissions to get access
to a reserve pool of NIPS tickets. So
please register to the workshop early.</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Call for submissions </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">We invite you to submit original work in, but not limited
to, following areas: </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Neural network compression techniques: </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Binarization, quantization, pruning, thresholding and coding
of neural networks </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Efficient computation and acceleration of deep convolutional
neural networks</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">deep neural network computation in low power consumption
applications (e.g., mobile or IoT devices) </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Differentiable sparsification and quantization of deep
neural networks</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Benchmarking of deep neural network compression techniques </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Neural network representation and exchange</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Exchange formats for (trained) neural networks</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Efficient deployment strategies for neural networks</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Industrial standardization of deep neural network
representations </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Performance evaluation methods of compressed networks in
application context (e.g., multimedia encoding and processing)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Video & media compression methods using DNNs such as
those developed in MPEG group: </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">To improve video coding standard development by using deep
neural networks </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">To increase practical applicability of network compression
methods</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">An extended abstract (3 pages long using NIPS style, see
<a href="https://nips.cc/Conferences/2018/PaperInformation/StyleFiles">https://nips.cc/Conferences/2018/PaperInformation/StyleFiles</a>) in PDF format
should be submitted for evaluation of the originality and quality of the
work. The evaluation is double-blind and
the abstract must be anonymous. References
may extend beyond the 3 page limit, and parallel submissions to a journal or
conferences (e.g. AAAI or ICLR) are permitted.
</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Submissions will be accepted as contributed talks (oral) or
poster presentations. Extended abstract should be submitted by 20 Oct 2018
through OpenReview. Submission details
will be updated at the workshop website http:address_here. All accepted abstracts will be posted on the
workshop website and archived. The full
papers of all accepted abstracts will be recommended for considering
publication at an international journal.
</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Important dates</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Extended abstract submission deadline: 20 Oct 2018,
(3̶1̶ ̶O̶c̶t̶ ̶2̶0̶1̶8̶)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Acceptance notification: 29 Oct. 2018, (1̶6̶ ̶N̶o̶v̶e̶m̶b̶e̶r̶ ̶2̶0̶1̶8̶)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Camera ready submission: 12 November 2018, (3̶0̶
̶N̶o̶v̶e̶m̶b̶e̶r̶ ̶2̶0̶1̶8̶)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Workshop: 7 December 2018</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Submission</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Submit your extended abstract through OpenReivew system
(click here) </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Workshop schedule (tentative): </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">09:00 AM Opening
and Introduction (Talk)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">09:05 AM TBD
1 (Oral presentation)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">09:30 AM Bandwidth
efficient deep learning by model compression (Invited talk) Song Han, MIT and
Deephi</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">09:55 AM Neural
network compression in the wild: why aiming for high compression factors is not
enough (Invited talk) Tim Genewein,
Bosch Center for AI and DeepMind</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">10:20 AM TBD
2 (Oral presentation)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">10:45 AM Coffee
break (morning) (break)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">11:00 AM Network
compression via differentiable pruning and quantization (Invited talk) Christos
Louizos</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">11:25 AM Deep
neural networks for multimedia processing, coding and standardization (Invited
talk) Shan Liu, Tencent Media Lab</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">11:50 AM TBD
3 (Oral presentation)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">12:15 PM Lunch
break (on your own) (break)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">02:00 PM Efficient
Computation of Deep Convolutional Neural Networks: A Quantization Perspective
(Invited talk) Jian Cheng, Institute of Automation, China</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">02:25 PM Deep
neural network compression and acceleration (Invited talk) Anbang Yao, Intel
labs China</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">02:50 PM TBD
4 (Oral presentation)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">03:15 PM Coffee
break (afternoon) (break)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">03:30 PM Poster
presentations TBD (Poster session)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">04:30 PM Panel
disucssion</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">05:30 PM Invited
talk (TBD) (Invited talk)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">05:55 PM Closing
(Talk)</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">NIPS Complimentary workshop registration:</p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">We will help authors of accepted submissions to get access
to a reserve pool of NIPS tickets. So
please register to the workshop early. </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif"> </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Organizers: </p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Lixin Fan, Nokia Technologies <<a href="mailto:lixin.fan@nokia.com">lixin.fan@nokia.com</a>></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Zhouchen Lin, Peking University <<a href="mailto:zlin@pku.edu.cn">zlin@pku.edu.cn</a>></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Max Welling, Qualcomm & University of Amsterdam, <<a href="mailto:welling.max@gmail.com">welling.max@gmail.com</a>></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Yurong Chen, Intel Labs China, <<a href="mailto:yurong.chen@intel.com">yurong.chen@intel.com</a>></p>
<p class="MsoNormal" style="margin:0cm 0cm 0.0001pt;font-size:11pt;font-family:Calibri,sans-serif">Werner Bailer, Joanneum Research,
<<a href="mailto:werner.bailer@joanneum.at">werner.bailer@joanneum.at</a>></p></div>