MCPcopy Create free account

hub / github.com/ddbourgin/numpy-ml / types & classes

Types & classes166 in github.com/ddbourgin/numpy-ml

⨍ Functions 1,202◇ Types & classes 166
↓ 22 callersClassAffine
numpy_ml/neural_nets/activations/activations.py:342
↓ 19 callersClassReLU
A rectified linear activation function. Notes ----- "ReLU units can be fragile during training and can "die". For example, a lar
numpy_ml/neural_nets/activations/activations.py:73
↓ 18 callersClassSigmoid
numpy_ml/neural_nets/activations/activations.py:30
↓ 17 callersClassActivationInitializer
numpy_ml/neural_nets/initializers/initializers.py:41
↓ 16 callersClassTanh
numpy_ml/neural_nets/activations/activations.py:304
↓ 14 callersClassFullyConnected
numpy_ml/neural_nets/layers/layers.py:2010
↓ 11 callersClassWeightInitializer
numpy_ml/neural_nets/initializers/initializers.py:242
↓ 8 callersClassConstantScheduler
numpy_ml/neural_nets/schedulers/schedulers.py:43
↓ 8 callersClassConv2D
numpy_ml/neural_nets/layers/layers.py:2895
↓ 8 callersClassExponentialScheduler
numpy_ml/neural_nets/schedulers/schedulers.py:72
↓ 8 callersClassLinearRegression
numpy_ml/linear_models/linear_regression.py:6
↓ 8 callersClassNoamScheduler
numpy_ml/neural_nets/schedulers/schedulers.py:144
↓ 8 callersClassTorchLinearActivation
numpy_ml/tests/nn_torch_models.py:124
↓ 7 callersClassELU
numpy_ml/neural_nets/activations/activations.py:412
↓ 6 callersClassBanditTrainer
numpy_ml/bandits/trainer.py:79
↓ 6 callersClassBatchNorm2D
numpy_ml/neural_nets/layers/layers.py:969
↓ 6 callersClassDecisionTree
numpy_ml/trees/dt.py:21
↓ 6 callersClassDiGraph
numpy_ml/utils/graphs.py:173
↓ 6 callersClassSoftPlus
numpy_ml/neural_nets/activations/activations.py:669
↓ 5 callersClassAdd
numpy_ml/neural_nets/layers/layers.py:633
↓ 5 callersClassEdge
numpy_ml/utils/graphs.py:12
↓ 5 callersClassGELU
numpy_ml/neural_nets/activations/activations.py:210
↓ 5 callersClassKNN
numpy_ml/nonparametric/knn.py:9
↓ 5 callersClassKingScheduler
numpy_ml/neural_nets/schedulers/schedulers.py:198
↓ 5 callersClassLeakyReLU
'Leaky' version of a rectified linear unit (ReLU). Notes ----- Leaky ReLUs [*]_ are designed to address the vanishing gradient probl
numpy_ml/neural_nets/activations/activations.py:140
↓ 4 callersClassConv1D
numpy_ml/neural_nets/layers/layers.py:2603
↓ 4 callersClassDict
numpy_ml/utils/data_structures.py:478
↓ 4 callersClassGradientBoostedDecisionTree
numpy_ml/trees/gbdt.py:18
↓ 4 callersClassLSTMCell
numpy_ml/neural_nets/layers/layers.py:3782
↓ 4 callersClassLeaf
numpy_ml/trees/dt.py:12
↓ 4 callersClassLinearKernel
numpy_ml/utils/kernels.py:72
↓ 4 callersClassRandomForest
numpy_ml/trees/rf.py:11
↓ 4 callersClassSELU
r""" A scaled exponential linear unit (SELU). Notes ----- SELU units, when used in conjunction with proper weight initialization and
numpy_ml/neural_nets/activations/activations.py:532
↓ 4 callersClassSoftmax
numpy_ml/neural_nets/layers/layers.py:2192
↓ 4 callersClassToken
numpy_ml/preprocessing/nlp.py:573
↓ 4 callersClassTrainer
numpy_ml/rl_models/trainer.py:5
↓ 3 callersClassAdditiveNGram
numpy_ml/ngram/ngram.py:364
↓ 3 callersClassBallTreeNode
numpy_ml/utils/data_structures.py:176
↓ 3 callersClassDropout
numpy_ml/neural_nets/wrappers/wrappers.py:152
↓ 3 callersClassGPRegression
numpy_ml/nonparametric/gp.py:18
↓ 3 callersClassKernelInitializer
numpy_ml/utils/kernels.py:241
↓ 3 callersClassKernelRegression
numpy_ml/nonparametric/kernel_regression.py:4
↓ 3 callersClassMLENGram
numpy_ml/ngram/ngram.py:313
↓ 3 callersClassMultinomialHMM
numpy_ml/hmm/hmm.py:7
↓ 3 callersClassNode
numpy_ml/trees/dt.py:4
↓ 3 callersClassOptimizerInitializer
numpy_ml/neural_nets/initializers/initializers.py:176
↓ 3 callersClassPolynomialKernel
numpy_ml/utils/kernels.py:119
↓ 3 callersClassPool2D
numpy_ml/neural_nets/layers/layers.py:3181
↓ 3 callersClassRBFKernel
numpy_ml/utils/kernels.py:184
↓ 3 callersClassSGD
numpy_ml/neural_nets/optimizers/optimizers.py:58
↓ 3 callersClassUCB1
numpy_ml/bandits/policies.py:187
↓ 2 callersClassAdaGrad
numpy_ml/neural_nets/optimizers/optimizers.py:156
↓ 2 callersClassAdam
numpy_ml/neural_nets/optimizers/optimizers.py:364
↓ 2 callersClassBallTree
numpy_ml/utils/data_structures.py:197
↓ 2 callersClassBayesianLinearRegressionKnownVariance
numpy_ml/linear_models/bayesian_regression.py:167
↓ 2 callersClassBayesianLinearRegressionUnknownVariance
numpy_ml/linear_models/bayesian_regression.py:8
↓ 2 callersClassCrossEntropy
numpy_ml/neural_nets/losses/losses.py:110
↓ 2 callersClassDiscreteSampler
numpy_ml/utils/data_structures.py:346
↓ 2 callersClassDotProductAttention
numpy_ml/neural_nets/layers/layers.py:139
↓ 2 callersClassEmbedding
numpy_ml/neural_nets/layers/layers.py:1811
↓ 2 callersClassEpsilonGreedy
numpy_ml/bandits/policies.py:101
↓ 2 callersClassExponential
numpy_ml/neural_nets/activations/activations.py:491
↓ 2 callersClassGoodTuringNGram
numpy_ml/ngram/ngram.py:459
↓ 2 callersClassHardSigmoid
numpy_ml/neural_nets/activations/activations.py:615
↓ 2 callersClassIdentity
numpy_ml/neural_nets/activations/activations.py:395
↓ 2 callersClassMultiply
numpy_ml/neural_nets/layers/layers.py:745
↓ 2 callersClassNCELoss
numpy_ml/neural_nets/losses/losses.py:514
↓ 2 callersClassNode
numpy_ml/preprocessing/nlp.py:399
↓ 2 callersClassRMSProp
numpy_ml/neural_nets/optimizers/optimizers.py:262
↓ 2 callersClassRNNCell
numpy_ml/neural_nets/layers/layers.py:3576
↓ 2 callersClassSchedulerInitializer
numpy_ml/neural_nets/initializers/initializers.py:106
↓ 2 callersClassSquaredError
numpy_ml/neural_nets/losses/losses.py:26
↓ 2 callersClassThompsonSamplingBetaBinomial
numpy_ml/bandits/policies.py:276
↓ 2 callersClassTorchBatchNormLayer
numpy_ml/tests/nn_torch_models.py:138
↓ 2 callersClassTorchCausalConv1d
https://github.com/pytorch/pytorch/issues/1333 NB: this is only ensures that the convolution out length is the same as the input length IFF s
numpy_ml/tests/nn_torch_models.py:541
↓ 2 callersClassTorchLayerNormLayer
numpy_ml/tests/nn_torch_models.py:216
↓ 2 callersClassTorchSDPAttentionLayer
numpy_ml/tests/nn_torch_models.py:1604
↓ 2 callersClassUndirectedGraph
numpy_ml/utils/graphs.py:266
↓ 2 callersClassVAELoss
numpy_ml/neural_nets/losses/losses.py:225
↓ 2 callersClassVocabulary
numpy_ml/preprocessing/nlp.py:1008
↓ 2 callersClassWGAN_GPLoss
numpy_ml/neural_nets/losses/losses.py:331
↓ 1 callersClassAdditiveGold
numpy_ml/tests/test_ngram.py:107
↓ 1 callersClassBatchNorm1D
numpy_ml/neural_nets/layers/layers.py:1218
↓ 1 callersClassBernoulliBandit
numpy_ml/bandits/bandits.py:142
↓ 1 callersClassBernoulliVAE
numpy_ml/neural_nets/models/vae.py:12
↓ 1 callersClassBidirectionalLSTM
numpy_ml/neural_nets/modules/modules.py:987
↓ 1 callersClassClassProbEstimator
numpy_ml/trees/losses.py:8
↓ 1 callersClassContextualLinearBandit
numpy_ml/bandits/bandits.py:421
↓ 1 callersClassCrossEntropyAgent
numpy_ml/rl_models/agents.py:101
↓ 1 callersClassCrossEntropyLoss
numpy_ml/trees/losses.py:52
↓ 1 callersClassDeconv2D
numpy_ml/neural_nets/layers/layers.py:3353
↓ 1 callersClassDynaAgent
numpy_ml/rl_models/agents.py:1304
↓ 1 callersClassEnvModel
A simple tabular environment model that maintains the counts of each reward-outcome pair given the state and action that preceded them. The
numpy_ml/rl_models/rl_utils.py:28
↓ 1 callersClassFlatten
numpy_ml/neural_nets/layers/layers.py:859
↓ 1 callersClassGMM
numpy_ml/gmm/gmm.py:7
↓ 1 callersClassGaussianNBClassifier
numpy_ml/linear_models/naive_bayes.py:5
↓ 1 callersClassGeneralizedLinearModel
numpy_ml/linear_models/glm.py:48
↓ 1 callersClassHuffmanEncoder
numpy_ml/preprocessing/nlp.py:431
↓ 1 callersClassIHT
Structure to handle collisions
numpy_ml/rl_models/tiles/tiles3.py:36
↓ 1 callersClassLDA
numpy_ml/lda/lda.py:5
next →1–100 of 166, ranked by callers