2016-2-28 今日收集

【论文:Burstiness Scale(BuSca)随机事件序列精简建模】《Burstiness Scale: a highly parsimonious model for characterizing random series of events》RAS Alves, R Assunção, POS de Melo (2016)O网页链接

【论文:基于Gradient Norm的CNN初始化参数优化RandomOut】《RandomOut: Using a convolutional gradient norm to win The Filter Lottery》J P Cohen, H Z. Lo, W Ding [University of Massachusetts Boston] (2016)O网页链接

《How many modes can a Gaussian mixture have?》by Carreira-Perpinan, M. A.O网页链接

【开源:openFrameworks的t-SNE降维可视化扩展】"t-SNE dimensionality reduction technique for openFrameworks" by Gene Kogan GitHub:O网页链接O网页链接

【论文:加速DNN训练的简单重参数化方法Weight Normalization】《Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks》T Salimans, D P. Kingma [Aidence & University of Amsterdam, OpenAI] (2016)O网页链接

【Nature Neuroscience:目标导向深度学习模型与感觉皮层】《Using goal-driven deep learning models to understand sensory cortex》DLK Yamins, JJ DiCarlo (2016)O网页链接

【手把手反向传播实例】《A Step by Step Backpropagation Example》by Matt MazurO网页链接  pdf:O网页链接

【论文:非凸优化逃离高阶鞍点的高效方法】《Efficient approaches for escaping higher order saddle points in non-convex optimization》A Anandkumar, R Ge [University of California & Duke University] (2016)O网页链接

【神经网络模型随机梯度下降法—简单实现与Torch应用】by@YushnengO网页链接

【两分钟论文解读系列——深度学习应用九则】《Two+ Minute Papers - 9 Cool Deep Learning Applications - YouTube》O网页链接O秒拍视频.