时间:2015-5-10下午3点
地点:蕴味儿咖啡(768创意产业园,在学清路上)
主讲人:曹旭东、孙铮、肖达
内容:
1. RNN/LSTM原理介绍,LSTM用于机器翻译的论文:Sequence to sequence learning with neural networks。肖达
2. LSTM用于图文翻译(看图说话)的论文:Show and tell: A neural image caption generator。曹旭东
3. 将注意机制引入图文翻译的论文:Show, Attend and Tell: Neural Image Caption Generation with Visual Attention。孙铮