{"version":1,"pages":[{"id":"r8tr8VGGPFnu0HaMDJ7k","title":"Machine Learning","pathname":"/","siteSpaceId":"sitesp_62mGF","description":""},{"id":"qOC9lIp9PNwngdv99N56","title":"Linear Model Cheating Sheet","pathname":"/machine-learning/linear-model-cheating-sheet","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"vj4q9YTQqWf8KCbgOHAq","title":"Nonlinear Model Cheating Sheet","pathname":"/machine-learning/nonlinear-model-cheating-sheet","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"F3qbQK3cR3Q9Mw7C5mAY","title":"General Linear Model 1","pathname":"/machine-learning/general-linear-model-1","siteSpaceId":"sitesp_62mGF","description":"Here are the notes for general linear regression.","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"EikhtHPbuDobPR0fMKOa","title":"General Linear Model 2","pathname":"/machine-learning/general-linear-model-2","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"S1wxEMrqjGKeBgvb5izA","title":"General Linear Model 3","pathname":"/machine-learning/general-linear-model-3","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"BaWmbaV3D2bfsS2iGPrs","title":"Tree Based Methods","pathname":"/machine-learning/tree-based-methods","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"kPczgZVOvxXiSrjJTGM9","title":"Tree Based Methods Supplement","pathname":"/machine-learning/tree-based-methods-supplement","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"JqEPx66E7mZOjKdRPEg4","title":"XG,Cat,Light__Boosting","pathname":"/machine-learning/xg-cat-light__boosting","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"mvQfsEM91HfFgDqNbV1g","title":"KNN&PCA","pathname":"/machine-learning/knn-and-pca","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"TIuLbjQ5ZWnlJv2li8Bw","title":"Model Performance","pathname":"/machine-learning/model-performance","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"6P3PwLuius2GBfSLFcey","title":"Model Evaluation","pathname":"/machine-learning/model-evaluation","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"ZAE2gKwHdWePF8UKJOs3","title":"Code Practice","pathname":"/machine-learning/code-practice","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"2JGN3Lepv0POR6gfl2Yw","title":"KNN","pathname":"/machine-learning/code-practice/knn","siteSpaceId":"sitesp_62mGF","description":"KNN","breadcrumbs":[{"label":"Machine Learning"},{"label":"Code Practice"}]},{"id":"yS5ZW9LUBpI5KKQclHxJ","title":"Decision Tree Python Code","pathname":"/machine-learning/code-practice/decision-tree-python-code","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning"},{"label":"Code Practice"}]},{"id":"iujiwyIuvTNdrwAJDQF7","title":"Data and Feature Engineering","pathname":"/machine-learning/data-and-feature-engineering","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning"}]},{"id":"Y8EjgiSeHCJ0NDEhmlYQ","title":"Handle Bias Data","pathname":"/machine-learning/data-and-feature-engineering/handle-bias-data","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning"},{"label":"Data and Feature Engineering"}]},{"id":"hSsejKzsuu3ngRauXMbz","title":"Cold Start Problem","pathname":"/machine-learning/data-and-feature-engineering/cold-start-problem","siteSpaceId":"sitesp_62mGF","description":"in recommendation system","breadcrumbs":[{"label":"Machine Learning"},{"label":"Data and Feature Engineering"}]},{"id":"GYbozYn2bKqHmy3XLJSZ","title":"Deep Learning","pathname":"/deep-learning","siteSpaceId":"sitesp_62mGF","description":""},{"id":"izJQKz4B9x07bhtR6LS4","title":"Summary v2","pathname":"/deep-learning/summary-v2","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"6PdNDpGvKFwNLIxdHSfD","title":"Basic Neural Network","pathname":"/deep-learning/basic-neural-network","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"lcXggYwdP8ixZKfJshTu","title":"From Linear to Deep","pathname":"/deep-learning/basic-neural-network/from-linear-to-deep","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic Neural Network"}]},{"id":"lxyy1YbdZZxdjl9na6Mk","title":"Perceptron and Activation Function","pathname":"/deep-learning/basic-neural-network/perceptron-and-activation-function","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic Neural Network"}]},{"id":"VHMJ4MMFfgdyzeE5vycI","title":"NN network Details","pathname":"/deep-learning/basic-neural-network/nn-network-details","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic Neural Network"}]},{"id":"BGxgLf8MaB3N3a8C3Xzt","title":"Backpropagation Details","pathname":"/deep-learning/basic-neural-network/backpropagation-details","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic Neural Network"}]},{"id":"fBtpVCe6tNoFVZHPFSNh","title":"Gradient Vanishing vs Gradient Exploding","pathname":"/deep-learning/basic-neural-network/gradient-vanishing-vs-gradient-exploding","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic Neural Network"}]},{"id":"0LuXqw78bQx9im6ExEpl","title":"Basic CNN","pathname":"/deep-learning/basic-cnn","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"EfTZ0cPKF9dBPkoDhRIe","title":"Why CNN","pathname":"/deep-learning/basic-cnn/why-cnn","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic CNN"}]},{"id":"iEOLnZ4CxeoFLclrO1qL","title":"Filter/ Convolution Kernel and Its Operation","pathname":"/deep-learning/basic-cnn/filter-convolution-kernel-and-its-operation","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic CNN"}]},{"id":"JOUL50GtWnIXJaBcbAyR","title":"Padding& Stride","pathname":"/deep-learning/basic-cnn/padding-and-stride","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic CNN"}]},{"id":"mkklz0lZT31h7e1QFYaV","title":"Layers","pathname":"/deep-learning/basic-cnn/layers","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic CNN"}]},{"id":"A0teZbqgwIhRXE7U3jJo","title":"Extra:From Fully Connected Layers to Convolutions","pathname":"/deep-learning/basic-cnn/extra-from-fully-connected-layers-to-convolutions","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic CNN"}]},{"id":"54XXpbMovZ33ShMkFv4T","title":"Extra: Multiple Input and Multiple Output Channels","pathname":"/deep-learning/basic-cnn/extra-multiple-input-and-multiple-output-channels","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic CNN"}]},{"id":"6J6gsXVofvyNYHSDf00o","title":"Advance CNN","pathname":"/deep-learning/advance-cnn","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"hgsRVqJb1qxsAoVI1UC8","title":"Convolutional Neural Networks(LeNet)","pathname":"/deep-learning/advance-cnn/convolutional-neural-networks-lenet","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"tuN2N0xeC4AYXzSlQBkQ","title":"Deep Convolution Neural Networks(AlexNet)","pathname":"/deep-learning/advance-cnn/deep-convolution-neural-networks-alexnet","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"Ew5KwkvfusMB3zu1HZHV","title":"Networks Using Blocks (VGG)","pathname":"/deep-learning/advance-cnn/networks-using-blocks-vgg","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"bg0fIbs2WQujrFSofzK8","title":"Network in Network(NiN)","pathname":"/deep-learning/advance-cnn/network-in-network-nin","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"PyDG3eJ0pKn4T4AoyOuX","title":"Multi-Branch Networks(GoogLeNet&I mageNet)","pathname":"/deep-learning/advance-cnn/multi-branch-networks-googlenet-and-i-magenet","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"mlNOxEcG3CiHdWYQnYf9","title":"Residual Networks(ResNet) and ResNeXt","pathname":"/deep-learning/advance-cnn/residual-networks-resnet-and-resnext","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"jwy4rJceE1fJCGbuE2Qr","title":"Densely Connected Networks(DenseNet)","pathname":"/deep-learning/advance-cnn/densely-connected-networks-densenet","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"d9jMgWpYNv5n4Qamvh2Q","title":"Batch Normalization","pathname":"/deep-learning/advance-cnn/batch-normalization","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance CNN"}]},{"id":"QdnEVQIV0POnlbEoi4n5","title":"Basic RNN","pathname":"/deep-learning/basic-rnn","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"5SfJSJm8GRGOW5kiLSz7","title":"Seq Model","pathname":"/deep-learning/basic-rnn/seq-model","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic RNN"}]},{"id":"WTHCXylrbxXGIHvBczST","title":"Raw Text to Seq","pathname":"/deep-learning/basic-rnn/raw-text-to-seq","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic RNN"}]},{"id":"1vXRJHrTzOp1ao9bC8ho","title":"Language Models","pathname":"/deep-learning/basic-rnn/language-models","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic RNN"}]},{"id":"rZr3WCumAKnS4yZK8Jlh","title":"Recurrent Neural Networks(RNN)","pathname":"/deep-learning/basic-rnn/recurrent-neural-networks-rnn","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic RNN"}]},{"id":"cQXLqeNgO4jLFjSI9tin","title":"Backpropagation Through Time","pathname":"/deep-learning/basic-rnn/backpropagation-through-time","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Basic RNN"}]},{"id":"NZizK3SZpxB3FauhUIYH","title":"Advance RNN","pathname":"/deep-learning/advance-rnn","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"CWoXKNsrWMGAcCRZK9Yx","title":"Gated Recurrent Units(GRU)","pathname":"/deep-learning/advance-rnn/gated-recurrent-units-gru","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance RNN"}]},{"id":"PHABxGl5C9QULIYFl8XM","title":"Long Short-Term Memory(LSTM)","pathname":"/deep-learning/advance-rnn/long-short-term-memory-lstm","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance RNN"}]},{"id":"uEZAb0kWk6BmFEU7J8eB","title":"Bidirectional Recurrent Neural Networks(BRNN)","pathname":"/deep-learning/advance-rnn/bidirectional-recurrent-neural-networks-brnn","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance RNN"}]},{"id":"Mq1sODdl8PRzZTssyGsf","title":"Encoder-Decoder Architecture","pathname":"/deep-learning/advance-rnn/encoder-decoder-architecture","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance RNN"}]},{"id":"Hu4XTp70HlBA0j0Q7VvG","title":"Seuqence to Sequence Learning(Seq2Seq)","pathname":"/deep-learning/advance-rnn/seuqence-to-sequence-learning-seq2seq","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Advance RNN"}]},{"id":"8PXz0il16SFaHsjpBu7V","title":"Attention Mechanisms and Transformers","pathname":"/deep-learning/attention-mechanisms-and-transformers","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"pl57HiQK0F2l1vjLBQOu","title":"Queries, Keys, and Values","pathname":"/deep-learning/attention-mechanisms-and-transformers/queries-keys-and-values","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"}]},{"id":"by4mMyBjqQzYVmduGwrB","title":"Attention is all you need","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"}]},{"id":"GHAovuEUXjeqIE80XJJH","title":"Attention and Kernel","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need/attention-and-kernel","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Attention is all you need"}]},{"id":"QOZWBexMdBdEPSWEIvC2","title":"Attention Scoring Functions","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need/attention-scoring-functions","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Attention is all you need"}]},{"id":"mRjoVkHoGYevDshZFBie","title":"The Bahdanau Attention Mechanism","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need/the-bahdanau-attention-mechanism","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Attention is all you need"}]},{"id":"XgZhbj3wjcfzCgOY1UM3","title":"Multi-Head Attention","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need/multi-head-attention","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Attention is all you need"}]},{"id":"ym3OAZx0N6j8BHdHz8ld","title":"Self-Attention","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need/self-attention","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Attention is all you need"}]},{"id":"FrIceQvE5IgtxQ4i6NoG","title":"Attention的实现","pathname":"/deep-learning/attention-mechanisms-and-transformers/attention-is-all-you-need/attention-de-shi-xian","siteSpaceId":"sitesp_62mGF","description":"Attention的实现","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Attention is all you need"}]},{"id":"vVKmp1QBsjWgtzr4J1tg","title":"The Transformer Architecture","pathname":"/deep-learning/attention-mechanisms-and-transformers/the-transformer-architecture","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"}]},{"id":"MASV35Ra3BxSzrKFXeCD","title":"Extra Reading","pathname":"/deep-learning/attention-mechanisms-and-transformers/the-transformer-architecture/extra-reading","siteSpaceId":"sitesp_62mGF","description":"Reading","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"The Transformer Architecture"}]},{"id":"zXqSeVyo72GqlR9zG0f8","title":"最短的最大路径长度","pathname":"/deep-learning/attention-mechanisms-and-transformers/the-transformer-architecture/zui-duan-de-zui-da-lu-jing-chang-du","siteSpaceId":"sitesp_62mGF","description":"Supplement","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"The Transformer Architecture"}]},{"id":"00wSVVPPNxr2WqY83ZMB","title":"Large-Scaling Pretraning with Transformers","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"}]},{"id":"CxqgQQBYn265YlXfpqwW","title":"BERT vs OpenAI GPT vs ELMo","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers/bert-vs-openai-gpt-vs-elmo","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Large-Scaling Pretraning with Transformers"}]},{"id":"N1KRaI5qdEEZvrEG7xaw","title":"Decoder Model框架","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers/decoder-model-kuang-jia","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Large-Scaling Pretraning with Transformers"}]},{"id":"3IcD9xWivVbxUHYPc7e1","title":"Bert vs XLNet","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers/bert-vs-xlnet","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Large-Scaling Pretraning with Transformers"}]},{"id":"DtC8DE61RUh8bDiFuZlC","title":"T5& GPT& Bert比较","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers/t5-gpt-bert-bi-jiao","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Large-Scaling Pretraning with Transformers"}]},{"id":"Iq7ZDhhBaA6WclcjMtXi","title":"编码器-解码器架构 vs GPT 模型","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers/bian-ma-qi-jie-ma-qi-jia-gou-vs-gpt-mo-xing","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Large-Scaling Pretraning with Transformers"}]},{"id":"TSQ0DtJllfXVZ43zTPYb","title":"Encoder vs Decoder Reference","pathname":"/deep-learning/attention-mechanisms-and-transformers/large-scaling-pretraning-with-transformers/encoder-vs-decoder-reference","siteSpaceId":"sitesp_62mGF","description":"Reference","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"},{"label":"Large-Scaling Pretraning with Transformers"}]},{"id":"YMbay9snKs0VAkwpOkEH","title":"Transformers for Vision","pathname":"/deep-learning/attention-mechanisms-and-transformers/transformers-for-vision","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"}]},{"id":"kiXecSNpeWLafdl028Ov","title":"Transformer for Multiomodal","pathname":"/deep-learning/attention-mechanisms-and-transformers/transformer-for-multiomodal","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"Attention Mechanisms and Transformers"}]},{"id":"68Dqc9zb4Ly6MnHOo78A","title":"NLP Pretraining","pathname":"/deep-learning/nlp-pretraining","siteSpaceId":"sitesp_62mGF","description":"NLP","breadcrumbs":[{"label":"Deep Learning"}]},{"id":"4oBexRVAfnAEhEfkx7mt","title":"Word Embedding(word2vec)","pathname":"/deep-learning/nlp-pretraining/word-embedding-word2vec","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"}]},{"id":"iqJkMSSFdNRUHExl77SP","title":"Extra Reading","pathname":"/deep-learning/nlp-pretraining/word-embedding-word2vec/extra-reading","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Word Embedding(word2vec)"}]},{"id":"y81pCg7ham3TL5aR1xYb","title":"Approximate Training","pathname":"/deep-learning/nlp-pretraining/approximate-training","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"}]},{"id":"UVaDSo0OGqpPrNQFt5r4","title":"Word Embedding with Global Vectors(GloVe)","pathname":"/deep-learning/nlp-pretraining/word-embedding-with-global-vectors-glove","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"}]},{"id":"cAk4CNzllENuLtWhLCRf","title":"Extra Reading","pathname":"/deep-learning/nlp-pretraining/word-embedding-with-global-vectors-glove/extra-reading","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Word Embedding with Global Vectors(GloVe)"}]},{"id":"9mU6eXlB1S1zvqCW1EvF","title":"Supplement","pathname":"/deep-learning/nlp-pretraining/word-embedding-with-global-vectors-glove/supplement","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Word Embedding with Global Vectors(GloVe)"}]},{"id":"RH9ot5amWVfYpU0G57wY","title":"Encoder(BERT)","pathname":"/deep-learning/nlp-pretraining/encoder-bert","siteSpaceId":"sitesp_62mGF","description":"Bidirectional Encoder Representations from Transformers(BERT)","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"}]},{"id":"SwjIVmuWY07XDvqUEmMa","title":"BERT","pathname":"/deep-learning/nlp-pretraining/encoder-bert/bert","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Encoder(BERT)"}]},{"id":"5WUVIGrSq4D6YIa7HjCO","title":"Extra Reading","pathname":"/deep-learning/nlp-pretraining/encoder-bert/extra-reading","siteSpaceId":"sitesp_62mGF","description":"Extra Reading","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Encoder(BERT)"}]},{"id":"1f5dyfoSkKt4ftI4ap47","title":"Decoder(GPT&XLNet&Lamma)","pathname":"/deep-learning/nlp-pretraining/decoder-gpt-and-xlnet-and-lamma","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"}]},{"id":"yoIfGu9OEk0Obi2XyqxH","title":"GPT","pathname":"/deep-learning/nlp-pretraining/decoder-gpt-and-xlnet-and-lamma/gpt","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Decoder(GPT&XLNet&Lamma)"}]},{"id":"XKNbijVCiRtyO6RbP4Li","title":"XLNet","pathname":"/deep-learning/nlp-pretraining/decoder-gpt-and-xlnet-and-lamma/xlnet","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Decoder(GPT&XLNet&Lamma)"}]},{"id":"fsXz1N4zLHPKKUVJxK9O","title":"XLNet架构","pathname":"/deep-learning/nlp-pretraining/decoder-gpt-and-xlnet-and-lamma/xlnet/xlnet-jia-gou","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Decoder(GPT&XLNet&Lamma)"},{"label":"XLNet"}]},{"id":"aFHm0Vqyce4AqrZZSauq","title":"XLNet特点与其他比较","pathname":"/deep-learning/nlp-pretraining/decoder-gpt-and-xlnet-and-lamma/xlnet/xlnet-te-dian-yu-qi-ta-bi-jiao","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Decoder(GPT&XLNet&Lamma)"},{"label":"XLNet"}]},{"id":"PpXqA6ZCC9IEqEpnmJoM","title":"Encoder-Decoder(BART& T5)","pathname":"/deep-learning/nlp-pretraining/encoder-decoder-bart-and-t5","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"}]},{"id":"Js0c3KkE5wxcfmkNIJTy","title":"BART","pathname":"/deep-learning/nlp-pretraining/encoder-decoder-bart-and-t5/bart","siteSpaceId":"sitesp_62mGF","description":"BART","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Encoder-Decoder(BART& T5)"}]},{"id":"nz652K6HFGeGxJLJklZL","title":"T5","pathname":"/deep-learning/nlp-pretraining/encoder-decoder-bart-and-t5/t5","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Deep Learning"},{"label":"NLP Pretraining"},{"label":"Encoder-Decoder(BART& T5)"}]},{"id":"aJJ1qe5YLi6C0lE691pp","title":"GenAI","pathname":"/genai","siteSpaceId":"sitesp_62mGF","description":"GenAI"},{"id":"aUGSvkzG0ymdig3GadcI","title":"Introduction","pathname":"/genai/introduction","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"}]},{"id":"K795DDo4X5nSFzyhAJip","title":"GenAI Paper Must Read","pathname":"/genai/introduction/genai-paper-must-read","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"GenAI"},{"label":"Introduction"}]},{"id":"LiKLB6fvfq41ZTmjEs8t","title":"GenAI六个阶段","pathname":"/genai/introduction/genai-liu-ge-jie-duan","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"GenAI"},{"label":"Introduction"}]},{"id":"QbbOx3ambhlS4w5RHuAo","title":"Language Models Pre-training","pathname":"/genai/language-models-pre-training","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"}]},{"id":"W48XhvZP4yXnOiiEjQo5","title":"Encoder-Decoder Architecture","pathname":"/genai/language-models-pre-training/encoder-decoder-architecture","siteSpaceId":"sitesp_62mGF","description":"o","breadcrumbs":[{"label":"GenAI"},{"label":"Language Models Pre-training"}]},{"id":"19UxFeW3VBULLAtrrni4","title":"Encoder Deep Dive","pathname":"/genai/language-models-pre-training/encoder-deep-dive","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"GenAI"},{"label":"Language Models Pre-training"}]},{"id":"kkfIHLxs2RSCHHe8h7Es","title":"Decoder Deep Dive","pathname":"/genai/language-models-pre-training/decoder-deep-dive","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"},{"label":"Language Models Pre-training"}]},{"id":"Tbu62T3PUvzZ13Fi5pqz","title":"Encoder VS Decoder","pathname":"/genai/language-models-pre-training/encoder-vs-decoder","siteSpaceId":"sitesp_62mGF","description":"Decoder","breadcrumbs":[{"label":"GenAI"},{"label":"Language Models Pre-training"}]},{"id":"AJaewCoxJcTjGvDf9eic","title":"Attention Mechanism","pathname":"/genai/language-models-pre-training/attention-mechanism","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"GenAI"},{"label":"Language Models Pre-training"}]},{"id":"nF3UqzhKqTR2IaY8G87k","title":"Transformers","pathname":"/genai/language-models-pre-training/transformers","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"},{"label":"Language Models Pre-training"}]},{"id":"CfNLDLf8DJi7EK6zFtrL","title":"Example: Llama 3 8B架构","pathname":"/genai/example-llama-3-8b-jia-gou","siteSpaceId":"sitesp_62mGF","description":"Llama3","breadcrumbs":[{"label":"GenAI"}]},{"id":"QYqqWj01TacV07mUn8hQ","title":"MoE layer","pathname":"/genai/moe-layer","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"}]},{"id":"1OkB15zvaDRu6ei3mIVC","title":"Fine-Tuning Generation Models","pathname":"/genai/fine-tuning-generation-models","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"}]},{"id":"Sbtw765bHn401l6otx8N","title":"RAG and Adavance RAG","pathname":"/genai/rag-and-adavance-rag","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"}]},{"id":"JjdPtR2tKKRNZ5Zfy8q9","title":"AI Agent","pathname":"/genai/ai-agent","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"GenAI"}]},{"id":"n9ekPXj2EpyLXmAxlDQb","title":"Statistics and Optimization","pathname":"/statistics-and-optimization","siteSpaceId":"sitesp_62mGF","description":""},{"id":"qE5y9uHMmgX2MoQ6hely","title":"A/B testing","pathname":"/statistics-and-optimization/a-b-testing","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Statistics and Optimization"}]},{"id":"EKyoGGPGRGttGauItJ4w","title":"Sampling/ABtesting/GradientMethod","pathname":"/statistics-and-optimization/sampling-abtesting-gradientmethod","siteSpaceId":"sitesp_62mGF","description":"Google Coding Summary","breadcrumbs":[{"label":"Statistics and Optimization"}]},{"id":"ip3botX83ujXeJAJcnmR","title":"Gradient Decent Deep Dive","pathname":"/statistics-and-optimization/gradient-decent-deep-dive","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Statistics and Optimization"}]},{"id":"Dt5TjVU9JoNY3cmy9pMT","title":"Machine Learning System Design","pathname":"/machine-learning-system-design","siteSpaceId":"sitesp_62mGF","description":""},{"id":"yU19vP4rX74PKgWI4ELM","title":"Extra Reading","pathname":"/machine-learning-system-design/extra-reading","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Machine Learning System Design"}]},{"id":"74ZzJz0YJp7SvnmCNJVu","title":"Introduction","pathname":"/machine-learning-system-design/introduction","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning System Design"}]},{"id":"161dfa5fc1473d90fd5fa66b6be39cc1f14a1f37","title":"Anomaly Detection","pathname":"/machine-learning-system-design/anomaly-detection","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning System Design"}]},{"id":"owAWdp5wSq7yzzyHTdnP","title":"6 Video Recommendation System","pathname":"/machine-learning-system-design/6-video-recommendation-system","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Machine Learning System Design"}]},{"id":"6tG1ntug61s4r5cH8NsJ","title":"Responsible AI","pathname":"/responsible-ai","siteSpaceId":"sitesp_62mGF","description":""},{"id":"UViF9XH4ty1bSrIcanKu","title":"AI Risk and Uncertainty","pathname":"/responsible-ai/ai-risk-and-uncertainty","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Responsible AI"}]},{"id":"UMrvio0q2YSE4c7YVTfq","title":"What is AI risk","pathname":"/responsible-ai/ai-risk-and-uncertainty/what-is-ai-risk","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"}]},{"id":"llex10ZIaV8DwfFRqdiO","title":"General Intro for Uncertainty Quantification","pathname":"/responsible-ai/ai-risk-and-uncertainty/general-intro-for-uncertainty-quantification","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"}]},{"id":"Uw8sM4VqjUsoj2v7Ai47","title":"Calibration","pathname":"/responsible-ai/ai-risk-and-uncertainty/calibration","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"}]},{"id":"9tE8lB9wbjtpY4M7ixsq","title":"Conformal Prediction","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"}]},{"id":"lTOyRfQdkhRvzpnFPp49","title":"Review the linear regression","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/review-the-linear-regression","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"kDKTlTatbtjtF8B3eyOC","title":"Exchangeability","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/exchangeability","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"EiZ5VsjHxG3qOYVRYiDL","title":"Split Conformal Prediction","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/split-conformal-prediction","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"bACkvZJXx1iBv42NdtjD","title":"Conformalized Quantile Regression","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/conformalized-quantile-regression","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"JUA4SYc1rOEMaqdY3YMG","title":"Beyond marginal coverage","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/beyond-marginal-coverage","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"DMdVHDvWpNWOYDpL3jTl","title":"Split Conformal Classification","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/split-conformal-classification","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"LVszhEvCQFQJyajTH0q7","title":"Full Conformal Coverage","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/full-conformal-coverage","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"7oQkIkWD3CiURGJiQsQm","title":"Cross-Validation +","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/cross-validation-+","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"tv1CopUbnU9sG0f8QE1D","title":"Conformal Histgram Regression","pathname":"/responsible-ai/ai-risk-and-uncertainty/conformal-prediction/conformal-histgram-regression","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Responsible AI"},{"label":"AI Risk and Uncertainty"},{"label":"Conformal Prediction"}]},{"id":"9ZVF9BsOOPTsbmAJA2uv","title":"xAI","pathname":"/responsible-ai/xai","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Responsible AI"}]},{"id":"NQne5HhfXqFONGfc1rNN","title":"SHAP value","pathname":"/responsible-ai/xai/shap-value","siteSpaceId":"sitesp_62mGF","description":"","breadcrumbs":[{"label":"Responsible AI"},{"label":"xAI"}]},{"id":"sz1z6xhTnkWCffPHn5qk","title":"Extra Research","pathname":"/extra-research","siteSpaceId":"sitesp_62mGF"},{"id":"VRtRMcvkIiC2qlqErr5y","title":"Paper Reading","pathname":"/extra-research/paper-reading","siteSpaceId":"sitesp_62mGF","breadcrumbs":[{"label":"Extra Research"}]},{"id":"O02CApqBr16GAMCXKT6P","title":"Reference","pathname":"/extra-research/reference","siteSpaceId":"sitesp_62mGF","description":"Referencee","breadcrumbs":[{"label":"Extra Research"}]}]}