https://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/distributions.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/eigendecomposition.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/geometry-linear-algebraic-ops.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/index.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/information-theory.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/integral-calculus.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/maximum-likelihood.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/multivariable-calculus.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/naive-bayes.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/random-variables.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/single-variable-calculus.htmlhttps://d2l-jp.me/chapter_appendix-mathematics-for-deep-learning/statistics.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/aws.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/colab.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/contributing.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/d2l.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/index.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/jupyter.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/sagemaker.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/selecting-servers-gpus.htmlhttps://d2l-jp.me/chapter_appendix-tools-for-deep-learning/utils.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/attention-pooling.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/attention-scoring-functions.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/bahdanau-attention.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/index.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/large-pretraining-transformers.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/multihead-attention.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/queries-keys-values.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/self-attention-and-positional-encoding.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/transformer.htmlhttps://d2l-jp.me/chapter_attention-mechanisms-and-transformers/vision-transformer.htmlhttps://d2l-jp.me/chapter_builders-guide/custom-layer.htmlhttps://d2l-jp.me/chapter_builders-guide/index.htmlhttps://d2l-jp.me/chapter_builders-guide/init-param.htmlhttps://d2l-jp.me/chapter_builders-guide/lazy-init.htmlhttps://d2l-jp.me/chapter_builders-guide/model-construction.htmlhttps://d2l-jp.me/chapter_builders-guide/parameters.htmlhttps://d2l-jp.me/chapter_builders-guide/read-write.htmlhttps://d2l-jp.me/chapter_builders-guide/use-gpu.htmlhttps://d2l-jp.me/chapter_computational-performance/async-computation.htmlhttps://d2l-jp.me/chapter_computational-performance/auto-parallelism.htmlhttps://d2l-jp.me/chapter_computational-performance/hardware.htmlhttps://d2l-jp.me/chapter_computational-performance/hybridize.htmlhttps://d2l-jp.me/chapter_computational-performance/index.htmlhttps://d2l-jp.me/chapter_computational-performance/multiple-gpus.htmlhttps://d2l-jp.me/chapter_computational-performance/multiple-gpus-concise.htmlhttps://d2l-jp.me/chapter_computational-performance/parameterserver.htmlhttps://d2l-jp.me/chapter_computer-vision/anchor.htmlhttps://d2l-jp.me/chapter_computer-vision/bounding-box.htmlhttps://d2l-jp.me/chapter_computer-vision/fcn.htmlhttps://d2l-jp.me/chapter_computer-vision/fine-tuning.htmlhttps://d2l-jp.me/chapter_computer-vision/image-augmentation.htmlhttps://d2l-jp.me/chapter_computer-vision/index.htmlhttps://d2l-jp.me/chapter_computer-vision/kaggle-cifar10.htmlhttps://d2l-jp.me/chapter_computer-vision/kaggle-dog.htmlhttps://d2l-jp.me/chapter_computer-vision/multiscale-object-detection.htmlhttps://d2l-jp.me/chapter_computer-vision/neural-style.htmlhttps://d2l-jp.me/chapter_computer-vision/object-detection-dataset.htmlhttps://d2l-jp.me/chapter_computer-vision/rcnn.htmlhttps://d2l-jp.me/chapter_computer-vision/semantic-segmentation-and-dataset.htmlhttps://d2l-jp.me/chapter_computer-vision/ssd.htmlhttps://d2l-jp.me/chapter_computer-vision/transposed-conv.htmlhttps://d2l-jp.me/chapter_convolutional-modern/alexnet.htmlhttps://d2l-jp.me/chapter_convolutional-modern/batch-norm.htmlhttps://d2l-jp.me/chapter_convolutional-modern/cnn-design.htmlhttps://d2l-jp.me/chapter_convolutional-modern/densenet.htmlhttps://d2l-jp.me/chapter_convolutional-modern/googlenet.htmlhttps://d2l-jp.me/chapter_convolutional-modern/index.htmlhttps://d2l-jp.me/chapter_convolutional-modern/nin.htmlhttps://d2l-jp.me/chapter_convolutional-modern/resnet.htmlhttps://d2l-jp.me/chapter_convolutional-modern/vgg.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/channels.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/conv-layer.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/index.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/lenet.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/padding-and-strides.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/pooling.htmlhttps://d2l-jp.me/chapter_convolutional-neural-networks/why-conv.htmlhttps://d2l-jp.me/chapter_gaussian-processes/gp-inference.htmlhttps://d2l-jp.me/chapter_gaussian-processes/gp-intro.htmlhttps://d2l-jp.me/chapter_gaussian-processes/gp-priors.htmlhttps://d2l-jp.me/chapter_gaussian-processes/index.htmlhttps://d2l-jp.me/chapter_generative-adversarial-networks/dcgan.htmlhttps://d2l-jp.me/chapter_generative-adversarial-networks/gan.htmlhttps://d2l-jp.me/chapter_generative-adversarial-networks/index.htmlhttps://d2l-jp.me/chapter_glossary/action.htmlhttps://d2l-jp.me/chapter_glossary/actions.htmlhttps://d2l-jp.me/chapter_glossary/actuator.htmlhttps://d2l-jp.me/chapter_glossary/agents.htmlhttps://d2l-jp.me/chapter_glossary/algorithm.htmlhttps://d2l-jp.me/chapter_glossary/aligned.htmlhttps://d2l-jp.me/chapter_glossary/artificial-general-intelligence.htmlhttps://d2l-jp.me/chapter_glossary/backpropagation.htmlhttps://d2l-jp.me/chapter_glossary/binary-classification.htmlhttps://d2l-jp.me/chapter_glossary/cbow.htmlhttps://d2l-jp.me/chapter_glossary/censored-feedback.htmlhttps://d2l-jp.me/chapter_glossary/classification.htmlhttps://d2l-jp.me/chapter_glossary/cnn.htmlhttps://d2l-jp.me/chapter_glossary/contextual-bandit-problem.htmlhttps://d2l-jp.me/chapter_glossary/covariates.htmlhttps://d2l-jp.me/chapter_glossary/cpu.htmlhttps://d2l-jp.me/chapter_glossary/credit-assignment.htmlhttps://d2l-jp.me/chapter_glossary/cross-entropy.htmlhttps://d2l-jp.me/chapter_glossary/data.htmlhttps://d2l-jp.me/chapter_glossary/data-instance.htmlhttps://d2l-jp.me/chapter_glossary/data-point.htmlhttps://d2l-jp.me/chapter_glossary/dataset.htmlhttps://d2l-jp.me/chapter_glossary/deep.htmlhttps://d2l-jp.me/chapter_glossary/deep-learning.htmlhttps://d2l-jp.me/chapter_glossary/deep-reinforcement-learning.htmlhttps://d2l-jp.me/chapter_glossary/dense-convolutional-network.htmlhttps://d2l-jp.me/chapter_glossary/dimensionality.htmlhttps://d2l-jp.me/chapter_glossary/distribution-shift.htmlhttps://d2l-jp.me/chapter_glossary/end-to-end-training.htmlhttps://d2l-jp.me/chapter_glossary/exploit.htmlhttps://d2l-jp.me/chapter_glossary/explore.htmlhttps://d2l-jp.me/chapter_glossary/family.htmlhttps://d2l-jp.me/chapter_glossary/feature-engineering.htmlhttps://d2l-jp.me/chapter_glossary/firm.htmlhttps://d2l-jp.me/chapter_glossary/gpgpus.htmlhttps://d2l-jp.me/chapter_glossary/gpu.htmlhttps://d2l-jp.me/chapter_glossary/gradient-descent.htmlhttps://d2l-jp.me/chapter_glossary/hdd.htmlhttps://d2l-jp.me/chapter_glossary/hierarchical-classification.htmlhttps://d2l-jp.me/chapter_glossary/index.htmlhttps://d2l-jp.me/chapter_glossary/inputs.htmlhttps://d2l-jp.me/chapter_glossary/intelligent.htmlhttps://d2l-jp.me/chapter_glossary/layers.htmlhttps://d2l-jp.me/chapter_glossary/learning.htmlhttps://d2l-jp.me/chapter_glossary/learning-algorithm.htmlhttps://d2l-jp.me/chapter_glossary/loss-functions.htmlhttps://d2l-jp.me/chapter_glossary/machine-learning.htmlhttps://d2l-jp.me/chapter_glossary/markov-decision-process.htmlhttps://d2l-jp.me/chapter_glossary/model.htmlhttps://d2l-jp.me/chapter_glossary/multi-armed-bandit-problem.htmlhttps://d2l-jp.me/chapter_glossary/multi-label-classification.htmlhttps://d2l-jp.me/chapter_glossary/multiclass-classification.htmlhttps://d2l-jp.me/chapter_glossary/nas.htmlhttps://d2l-jp.me/chapter_glossary/neural-networks.htmlhttps://d2l-jp.me/chapter_glossary/nms.htmlhttps://d2l-jp.me/chapter_glossary/objective-function.htmlhttps://d2l-jp.me/chapter_glossary/objective-functions.htmlhttps://d2l-jp.me/chapter_glossary/observation.htmlhttps://d2l-jp.me/chapter_glossary/offline-learning.htmlhttps://d2l-jp.me/chapter_glossary/overfitting.htmlhttps://d2l-jp.me/chapter_glossary/parameters.htmlhttps://d2l-jp.me/chapter_glossary/personalization.htmlhttps://d2l-jp.me/chapter_glossary/policy.htmlhttps://d2l-jp.me/chapter_glossary/programming-with-data.htmlhttps://d2l-jp.me/chapter_glossary/regression.htmlhttps://d2l-jp.me/chapter_glossary/reinforcement-learning.htmlhttps://d2l-jp.me/chapter_glossary/right.htmlhttps://d2l-jp.me/chapter_glossary/rnn.htmlhttps://d2l-jp.me/chapter_glossary/sample.htmlhttps://d2l-jp.me/chapter_glossary/self-supervised-learning.htmlhttps://d2l-jp.me/chapter_glossary/seq2seq.htmlhttps://d2l-jp.me/chapter_glossary/sequence-learning.htmlhttps://d2l-jp.me/chapter_glossary/sequence-to-sequence-learning.htmlhttps://d2l-jp.me/chapter_glossary/sgd.htmlhttps://d2l-jp.me/chapter_glossary/squared-error.htmlhttps://d2l-jp.me/chapter_glossary/statistical-models.htmlhttps://d2l-jp.me/chapter_glossary/supervised-learning.htmlhttps://d2l-jp.me/chapter_glossary/surrogate-objective.htmlhttps://d2l-jp.me/chapter_glossary/target.htmlhttps://d2l-jp.me/chapter_glossary/text-to-speech.htmlhttps://d2l-jp.me/chapter_glossary/train.htmlhttps://d2l-jp.me/chapter_glossary/unsupervised-learning.htmlhttps://d2l-jp.me/chapter_glossary/vit.htmlhttps://d2l-jp.me/chapter_glossary/wake-word.htmlhttps://d2l-jp.me/chapter_hyperparameter-optimization/hyperopt-api.htmlhttps://d2l-jp.me/chapter_hyperparameter-optimization/hyperopt-intro.htmlhttps://d2l-jp.me/chapter_hyperparameter-optimization/index.htmlhttps://d2l-jp.me/chapter_hyperparameter-optimization/rs-async.htmlhttps://d2l-jp.me/chapter_hyperparameter-optimization/sh-async.htmlhttps://d2l-jp.me/chapter_hyperparameter-optimization/sh-intro.htmlhttps://d2l-jp.me/chapter_installation/index.htmlhttps://d2l-jp.me/chapter_introduction/index.htmlhttps://d2l-jp.me/chapter_linear-classification/classification.htmlhttps://d2l-jp.me/chapter_linear-classification/environment-and-distribution-shift.htmlhttps://d2l-jp.me/chapter_linear-classification/generalization-classification.htmlhttps://d2l-jp.me/chapter_linear-classification/image-classification-dataset.htmlhttps://d2l-jp.me/chapter_linear-classification/index.htmlhttps://d2l-jp.me/chapter_linear-classification/softmax-regression.htmlhttps://d2l-jp.me/chapter_linear-classification/softmax-regression-concise.htmlhttps://d2l-jp.me/chapter_linear-classification/softmax-regression-scratch.htmlhttps://d2l-jp.me/chapter_linear-regression/generalization.htmlhttps://d2l-jp.me/chapter_linear-regression/index.htmlhttps://d2l-jp.me/chapter_linear-regression/linear-regression.htmlhttps://d2l-jp.me/chapter_linear-regression/linear-regression-concise.htmlhttps://d2l-jp.me/chapter_linear-regression/linear-regression-scratch.htmlhttps://d2l-jp.me/chapter_linear-regression/oo-design.htmlhttps://d2l-jp.me/chapter_linear-regression/synthetic-regression-data.htmlhttps://d2l-jp.me/chapter_linear-regression/weight-decay.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/backprop.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/dropout.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/generalization-deep.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/index.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/kaggle-house-price.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/mlp.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/mlp-implementation.htmlhttps://d2l-jp.me/chapter_multilayer-perceptrons/numerical-stability-and-init.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/finetuning-bert.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/index.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/natural-language-inference-and-dataset.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/natural-language-inference-attention.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/natural-language-inference-bert.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/sentiment-analysis-and-dataset.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/sentiment-analysis-cnn.htmlhttps://d2l-jp.me/chapter_natural-language-processing-applications/sentiment-analysis-rnn.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/approx-training.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/bert.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/bert-dataset.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/bert-pretraining.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/glove.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/index.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/similarity-analogy.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/subword-embedding.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/word-embedding-dataset.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/word2vec.htmlhttps://d2l-jp.me/chapter_natural-language-processing-pretraining/word2vec-pretraining.htmlhttps://d2l-jp.me/chapter_notation/index.htmlhttps://d2l-jp.me/chapter_optimization/adadelta.htmlhttps://d2l-jp.me/chapter_optimization/adagrad.htmlhttps://d2l-jp.me/chapter_optimization/adam.htmlhttps://d2l-jp.me/chapter_optimization/convexity.htmlhttps://d2l-jp.me/chapter_optimization/gd.htmlhttps://d2l-jp.me/chapter_optimization/index.htmlhttps://d2l-jp.me/chapter_optimization/lr-scheduler.htmlhttps://d2l-jp.me/chapter_optimization/minibatch-sgd.htmlhttps://d2l-jp.me/chapter_optimization/momentum.htmlhttps://d2l-jp.me/chapter_optimization/optimization-intro.htmlhttps://d2l-jp.me/chapter_optimization/rmsprop.htmlhttps://d2l-jp.me/chapter_optimization/sgd.htmlhttps://d2l-jp.me/chapter_preface/index.htmlhttps://d2l-jp.me/chapter_preliminaries/autograd.htmlhttps://d2l-jp.me/chapter_preliminaries/calculus.htmlhttps://d2l-jp.me/chapter_preliminaries/index.htmlhttps://d2l-jp.me/chapter_preliminaries/linear-algebra.htmlhttps://d2l-jp.me/chapter_preliminaries/lookup-api.htmlhttps://d2l-jp.me/chapter_preliminaries/ndarray.htmlhttps://d2l-jp.me/chapter_preliminaries/pandas.htmlhttps://d2l-jp.me/chapter_preliminaries/probability.htmlhttps://d2l-jp.me/chapter_recommender-systems/autorec.htmlhttps://d2l-jp.me/chapter_recommender-systems/ctr.htmlhttps://d2l-jp.me/chapter_recommender-systems/deepfm.htmlhttps://d2l-jp.me/chapter_recommender-systems/fm.htmlhttps://d2l-jp.me/chapter_recommender-systems/index.htmlhttps://d2l-jp.me/chapter_recommender-systems/mf.htmlhttps://d2l-jp.me/chapter_recommender-systems/movielens.htmlhttps://d2l-jp.me/chapter_recommender-systems/neumf.htmlhttps://d2l-jp.me/chapter_recommender-systems/ranking.htmlhttps://d2l-jp.me/chapter_recommender-systems/recsys-intro.htmlhttps://d2l-jp.me/chapter_recommender-systems/seqrec.htmlhttps://d2l-jp.me/chapter_recurrent-modern/beam-search.htmlhttps://d2l-jp.me/chapter_recurrent-modern/bi-rnn.htmlhttps://d2l-jp.me/chapter_recurrent-modern/deep-rnn.htmlhttps://d2l-jp.me/chapter_recurrent-modern/encoder-decoder.htmlhttps://d2l-jp.me/chapter_recurrent-modern/gru.htmlhttps://d2l-jp.me/chapter_recurrent-modern/index.htmlhttps://d2l-jp.me/chapter_recurrent-modern/lstm.htmlhttps://d2l-jp.me/chapter_recurrent-modern/machine-translation-and-dataset.htmlhttps://d2l-jp.me/chapter_recurrent-modern/seq2seq.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/bptt.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/index.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/language-model.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/rnn.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/rnn-concise.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/rnn-scratch.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/sequence.htmlhttps://d2l-jp.me/chapter_recurrent-neural-networks/text-sequence.htmlhttps://d2l-jp.me/chapter_references/zreferences.htmlhttps://d2l-jp.me/chapter_reinforcement-learning/index.htmlhttps://d2l-jp.me/chapter_reinforcement-learning/mdp.htmlhttps://d2l-jp.me/chapter_reinforcement-learning/qlearning.htmlhttps://d2l-jp.me/chapter_reinforcement-learning/value-iter.htmlhttps://d2l-jp.me/index.htmlhttps://d2l-jp.me/genindex.htmlhttps://d2l-jp.me/search.html