标签

目前共计 165 个标签
ACT Attentive Pooling Auto-encoder BERT Backpropagation Bilinear CCNet CHI CNN Classification CoVe Convolution Cutout Deep Reinforcement Learning DiSAN DropConnect Dropout ELMo Embedding Encode Ensemble GC-Net GCNN GE-Net GPT Generation GloVe Google Gradient Descent HAN LSTM Language Modeling Linear Dimension Reduction Linux Logistic Regression Mac NLP🤖 NMT NTM Neighbor Embedding Non-local Normalization Numpy Optimizer Ordered Neuron PRML PSANet Paper Parameter Probabilistic Generative Model Probability Calibration Pycharm Python Python tricks Pytorch RNN SE-Net SK-Net SVM Semi-supervised learning Softmax TCN Targeted Dropout Tf-idf Tips for DL Transfer Learning Transformer Transformer-XL Trellis Networks ULMFiT Unsupervised Learning Vim XGBoost app attention attention mechanism attentional pooling backward bias&variance bpc bug capsule code snippets conda contextualized embedding continuous decoding double attention dropblock dropout eager translation model embedding fairseq grad hexo index_coopy intrinsic dimension learning rate locality modeling long-term dependency mask矩阵 nan nested attention nohup padding perplexity pooling positional encoding pretrain regularization rel-shift relative position sampling second-order self-attention sentence embedding sparse gradient ssh text classification transformer transformer-xl tricks yield 代码实践 代码片段 优化算法 佳句分享 协方差 参数初始化 困惑度 度量标准 快捷键 情感分析 技巧 拷贝 指南 教程 文本分类 有感 机器学习🤖 机器翻译 杂七杂八 李宏毅机器学习课程 梯度消失 梯度爆炸 概率校准 正态分布 每周论文阅读 比赛 求导 活动 深度学习🤖 碎片知识 笔记📒 网络 莱斯杯 词向量 诗词 诗词分享 调参 调参技巧 调参方法 达观杯 遇到的问题 配置 采样