logo
  • Welcome to MorphoLayers
  • Basics on Mathematical Morphology
  • Initializers
  • First Steps on training a Deep Learning model
  • Regularizing a Morphological Layer for Deep Learning
  • Comparing layers: a practical case on Mnist
  • Comparing layers: a practical case on Fashion Mnist
  • References
  • Acknowledgements
  • About the author
  • Index
Powered by Jupyter Book

Index

A | B | C | D | E | F | G | I | L | M | O | P | Q | R | S | T

A

  • absortion law
  • activation function
  • ADAM
  • architecture

B

  • back-propagation
  • Beucher gradient

C

  • Callbacks
  • classification report
  • closing
  • closing by reconstruction
  • compositional map
  • confusion matrix
  • contrast mapping

D

  • Deep Neural Network
  • dilation

E

  • EarlyStopping
  • Elastic net regularization
  • empirical risk
  • epoch
  • erosion

F

  • F1 score

G

  • geodesic dilation

I

  • Initializers
  • internal gradient

L

  • L1L2Lattice
  • L1Lattice
  • L2Lattice
  • Lasso regularization
  • learning rate
  • loss function

M

  • macro-average
  • micro-average
  • minibatch
  • MinusOnesZeroCenter
  • morphological probing
  • morphological reconstruction

O

  • opening
  • opening by reconstruction

P

  • positive predictive value
  • Precision
  • Projected Gradient Descent

Q

  • Quadratic

R

  • RandomLattice
  • RandomNegativeLattice
  • RandomwithMaxLattice
  • RandomwithMinLattice
  • RandomwithZeroLattice
  • Recall
  • ReduceLROnPlateau
  • Ridge regularization

S

  • sensitivity
  • SignedOnes
  • SparseNumZeros
  • SparseZeros
  • Standard gradient descent
  • stochastic gradient descend
  • Stochastic Gradient Descent

T

  • Tikhonov regularization
  • toggle mapping
  • Top-hat transform

By Santiago VELASCO-FORERO
© Copyright 2020.