Google DeepMind发布的Projected Natural Gradient Descent算法(PRONG)在使用批规范化(Batch Normalization)后，展现出优于随机梯度下降(SGD)的性能提升。此外，介绍了一种深度卷积匹配技术，以及利用卷积神经网络识别植物的DEEP-PLANT项目，还探讨了深度神经网络用于大规模图像搜索的语义保存哈希技术，以及注意力网络在精确目标检测中的应用。
Natural Neural Networks
Google DeepMind又一神作
Projected Natural Gradient Descent algorithm (PRONG) better than SGD as evidenced by the boost in performance offered by batch normalization (BN)
Deep Convolutional Matching
DEEP-PLANT: PLANT IDENTIFICATION WITHCONVOLUTIONAL NEURAL NETWORKS
Supervised Learning of Semantics-PreservingHashing via Deep Neural Networks for Large-Scale Image Search
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
