MLPClassifier

#include <Skigen/NeuralNetwork>

template <typename Scalar = double>
class Skigen::MLPClassifier(hidden_layer_sizes={100}, activation=MLPActivation::ReLU, solver=MLPSolver::Adam, alpha=1e-4, learning_rate_init=1e-3, max_iter=200, tol=1e-4, batch_size=0, random_state=std::nullopt, beta_1=0.9, beta_2=0.999, epsilon=1e-8)

Multi-layer perceptron classifier (binary + multiclass).

Mirrors sklearn.neural_network.MLPClassifier.

Architecture: hidden layers with the chosen activation, followed by a logistic (sigmoid) output unit for binary or softmax for multiclass. Trained by mini-batch SGD or Adam on the cross-entropy loss with L2 weight regularisation (alpha).

---

---

Attributes:

• hidden_layer_sizes : const std::vector< int > &

• activation : MLPActivation

• solver : MLPSolver

• classes : const Eigen::VectorXi

• n_classes : int

• n_iter_run : int

• loss : Scalar

• coefs : const std::vector< MatrixType > &

• intercepts : const std::vector< VectorType > &

---

Methods

SKIGEN_PARAMS()

---

predict(X)

---

predict_proba(X)

Probability matrix shape (n_samples, n_classes).

---