Ensure inputs to an estimator are in the expected format. Ensures X and y are stored as numpy ndarrays by converting from an array-li

Increase specific weight by amount of the step parameter.

Update gradient values.

Splits X into equal sized chunks.

Calculate output shape for convolution layer.

Calculate gain for split search.

Return activation function by name

Returns initialization function by the name.

First order gradient.

Init gradient arrays corresponding to each weight array.

Base class for RandomForest. Parameters ---------- n_estimators : int The number of decision tree. max_fe

Apply regularization to the loss.

Error for single example.

Initialize model's layers.

Rearrange columns into image blocks. Parameters ---------- columns images_shape : tuple(n_images, n_channels, height, width) filt

Perform Expectation–Maximization (EM) until converged.

Forward propagation.

Return metric function by name

Second order gradient.

Rearrange image blocks into columns. Parameters ---------- filter_shape : tuple(height, width) images : np.array, shape (n_images, n

Predict single row.

Build a decision tree from training set. Parameters ---------- X : array-like Feature dataset. target :

Performs an update of parameters.

Expectation(E-step) for Gaussian Mixture.

Maximization (M-step) for Gaussian Mixture.

Performs binary search to find suitable precision.

Find optimal value for leaf.

Find the closest centroid for a point.

Calculate distance from centers.

Find best feature and value for a split. Greedy algorithm.

Find L and H such that L <= alpha <= H. Also, alpha must satisfy the constraint 0 <= αlpha <= C.

Find entry layer for back propagation.

Find all possible split values.

Get values by indices and take the mean.

Computes pairwise affinities.

Set the initial weights, means and covs (with full covariance matrix). weights: the prior of the clusters (what percentage of data does a clu

Set the initial centroids.

Check if the distance between old and new centroids is zero.

Check if the difference of the latest two likelihood is less than the tolerance.

Calculate Gaussian PDF for each feature.

Predict the label of a single instance x.

Computes Student t-distribution.