-
### Motivation
최근 DNN 모델은 더욱 큰 메모리 공간을 요구한다. 하지만 GPU, TPU와 같은 전통적인 HBM 기반 DNN training platform은 불충분한 용량을 제공할 뿐 아니라, 추가적인 비용과 memory bandwidth 측면에서의 under-utilization을 유발한다.
### Proposal
저자들은 비용 …
-
https://www.usenix.org/conference/nsdi23/presentation/zhang-hong
-
Can you share the working codebase to replicate paper results for ImageNet with MixedPrecisionQuantization?
-
Training DNNs uses random resize, crop, rotation, etc. for data augmentation. How do you do this with jpeg2dct?
-
https://arxiv.org/pdf/2006.02464.pdf
终于找到一篇挂arXiv上的
-
[Explaining the Unexplained: A CLass-Enhanced Attentive Response (CLEAR) Approach to Understanding Deep Neural Networks](http://ieeexplore.ieee.org/document/8014949/)
In this work, we propose CLass-E…
-
[Interpretable deep neural networks for single-trial EEG classification](https://www.sciencedirect.com/science/article/pii/S0165027016302333)
_Background_
In cognitive neuroscience the potential of …
-
Hi, I see from the documentation that MFA can use DNNS based on Kaldi's nnet2 recipes. Any plan to use nnet3?
Thanks
-
Anyone has interest to utilize the sparsity to accelerate DNNs?
I am working on the fork https://github.com/wenwei202/caffe/tree/scnn and currently, on average, achieve ~5x CPU and ~3x GPU layer-wi…
-
Hay.Nowdays, I am interesting in Biomedical Signal Processing by deep learning. I am confused by the biosignal sequence to extract data for learning model.So that I had to study the papers your shared…