Deep learning, and in particular Recurrent Neural Networks (RNN) have shown
superior accuracy in a large variety of tasks including machine translation,
language understanding, and movie frame generation. However, these deep
learning approaches are very expensive in terms of computation. In most cases,
Graphic Processing Units (GPUs) are in used for large scale implementations.
Meanwhile, energy efficient RNN approaches are proposed for deploying solutions
on special purpose hardware including Field Programming Gate Arrays (FPGAs) and
mobile platforms. In this paper, we propose an effective quantization approach
for Recurrent Neural Networks (RNN) techniques including Long Short Term Memory
(LSTM), Gated Recurrent Units (GRU), and Convolutional Long Short Term Memory
(ConvLSTM). We have implemented different quantization methods including Binary
Connect {-1, 1}, Ternary Connect {-1, 0, 1}, and Quaternary Connect {-1, -0.5,
0.5, 1}. These proposed approaches are evaluated on different datasets for
sentiment analysis on IMDB and video frame predictions on the moving MNIST
dataset. The experimental results are compared against the full precision
versions of the LSTM, GRU, and ConvLSTM. They show promising results for both
sentiment analysis and video frame prediction.

本文提出了一种有效的量化方法，可用于将循环神经网络（包括 LSTM，GRU 和 ConvLSTM）部署在 FPGA 和移动平台上，同时在 IMDB 情感分析和移动 MNIST 视频帧预测等数据集上取得了有希望的成果。

循环神经网络的有效量化方法

Effective Quantization Approaches for Recurrent Neural Networks

In this work we propose a simple unsupervised approach for next frame
prediction in video. Instead of directly predicting the pixels in a frame given
past frames, we predict the transformations needed for generating the next
frame in a sequence, given the transformations of the past frames. This leads
to sharper results, while using a smaller prediction model. In order to enable
a fair comparison between different video frame prediction models, we also
propose a new evaluation protocol. We use generated frames as input to a
classifier trained with ground truth sequences. This criterion guarantees that
models scoring high are those producing sequences which preserve discriminative
features, as opposed to merely penalizing any deviation, plausible or not, from
the ground truth. Our proposed approach compares favourably against more
sophisticated ones on the UCF-101 data set, while also being more efficient in
terms of the number of parameters and computational cost.

本文提出了一种基于无监督方法的视频帧预测技术，相比直接预测未来帧中每个像素点，本文预测未来帧的变换过程，同时提出了一种新的评估协议，该方法在 UCF-101 数据集上进行了验证，在参数和计算成本上更加高效。