[Fri, 3 Jul 2015 ~ Tue, 7 Jul 2015] Deep Learning in arxiv

本文探讨了使用注意力机制的编码器-解码器网络来描述多媒体内容的方法,并涉及机器翻译、语音识别及图像标注等领域的应用。同时介绍了端到端卷积网络在显著性预测中的作用及其实现方式。

Convolutional Color Constancy

can this be used for training cnn to narrow the gap between different lighting conditions?

 

Describing Multimedia Content using Attention-based Encoder–Decoder Networks

lots of machine translation, speech recognition, image caption related reference

 

End-to-end Convolutional Network for Saliency Prediction

theano based code: https://imatge.upc.edu/web/resources/end-end-convolutional-networks-saliency-prediction-software

 

EXPERIMENTS ON PARALLEL TRAINING OF DEEPNEURAL NETWORK USING MODEL AVERAGING

mpi for multi-gpu solution

 

A linear approach for sparse coding by atwo-layer neural network


评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值