We invite you to submit original work in, but not limited to, following areas:

 

Neural network compression techniques:

• Binarization, quantization, pruning, thresholding and coding of neural networks

• Efficient computation and acceleration of deep convolutional neural networks

• deep neural network computation in low power consumption applications (e.g., mobile or IoT devices) Differentiable sparsification and quantization of deep neural networks

• Benchmarking of deep neural network compression techniques

 

Neural network representation and exchange

• Exchange formats for (trained) neural networks

• Efficient deployment strategies for neural networks

• Industrial standardization of deep neural network representations

• Performance evaluation methods of compressed networks in application context (e.g., multimedia encoding and processing)

 

Video & media compression methods using DNNs such as those developed in MPEG group:

• To improve video coding standard development by using deep neural networks   

• To increase practical applicability of network compression methods

 

An extended abstract (3 pages long using NIPS style, see https://nips.cc/Conferences/2018/PaperInformation/StyleFiles ) 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.  

 

Submissions will be accepted as contributed talks (oral) or poster presentations. Extended abstract should be submitted by 20 Oct 2018 through OpenReview (here).  All accepted abstracts will be posted on the workshop website and archived.