Re: [AIRG] Model Compression -- Binarized Neural Network

[Aubrey Barnard <barnard@xxxxxxxxxxx>]

Here's the published version of the paper (which, based on a quick check 
of a few spots, is more polished):

http://papers.nips.cc/paper/6573-binarized-neural-networks

On 11/7/18 9:54 AM, Aubrey Barnard wrote:
> AIRG,
> 
> I would like to remind you all that later today Xianda (Bryce) Xu will
> be presenting on binarized deep neural networks, which are more
> efficient in terms of speed and memory than regular ones while still
> performing just as (or more) accurately.
> 
> 4pm, CS 3310
> https://arxiv.org/abs/1602.02830
> 
> See you there!
> 
> Aubrey
> 
> 
> On 10/31/18 6:37 PM, Bryce XU via AIRG wrote:
>> Hi, everyone!
>>
>>
>> I am a visiting Junior undergraduate from University of Electronic
>> Science and Technology of China.
>>
>>
>> Next Wednesday ( 7th Nov. ), I would like to share you guys with
>> something about Model Compression.
>>
>>
>> I will first talk about the significance of model compression in
>> artificial intelligence and possible solutions. Then, I will show you
>> how to binarize the model in order to compress and speed it up.
>> Afterwards, I will talk a little bit about my experiments and some
>> problems we may encounter in binarizing the model. Last, some recent
>> work will be covered.
>>
>>
>> The paper you need to read is https://arxiv.org/abs/1602.02830.
>>
>>
>> I will also give you some optional papers if you are interested in this
>> topic.
>>
>> http://papers.nips.cc/paper/5647-binaryconnect-training-deep-neural-networks-with-b
>> https://link.springer.com/chapter/10.1007/978-3-319-46493-0_32
>>
>> https://arxiv.org/abs/1612.01064
>>
>> https://arxiv.org/abs/1806.07550
>>
>>
>> Best,
>>
>>
>> Xianda (Bryce) Xu
>>
>> [1602.02830] Binarized Neural Networks: Training Deep ...
>> <https://arxiv.org/abs/1602.02830>
>> arxiv.org
>> Abstract: We introduce a method to train Binarized Neural Networks
>> (BNNs) - neural networks with binary weights and activations at
>> run-time. At training-time the binary weights and activations are used
>> for computing the parameters gradients. During the forward pass, BNNs
>> drastically reduce memory size and accesses, and replace most arithmetic
>> operations with bit-wise operations, which is ...
>>
>>
>>
>>
>>
>>
>> _______________________________________________
>> AIRG mailing list
>> AIRG@xxxxxxxxxxx
>> https://lists.cs.wisc.edu/mailman/listinfo/airg
>>
> 
> _______________________________________________
> AIRG mailing list
> AIRG@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/airg
>