Greife auf kostenlose Karteikarten, Zusammenfassungen, Übungsaufgaben und Altklausuren für deinen ML interview Kurs an der Université Ibn Zohr Agadir zu.
693
Karteikarten
328
Studierende
1
Lernmaterialien
Feature Extraction
A slightly less common, more specialized approach to deep learning is to use the network as a feature extractor. Since all the layers are tasked with learning certain features from images, we can pull these features out of the network at any time during the training process. These features can then be used as input to a machine learning model such as support vector machines (SVM).
3. Fit the model
What is an API?
An application programming interface is a connection between computers or between computer programs.
4. Regularization
Regularization reduce overfitting by adding penalty to all features which are useless
Dropout is an approach of regularization in NN
value of dropout vary from 0 to 1
0 => no dropout
0.2 => 20% of all neurons from hidden layer is removed
1. Activation function
transform the data provided by input layer into output layer that are needed to a NN to function
f(x) = x ; do not help with complexity of problem
most used makes it easy for the model to adapt or generalize with a varity of data + derivative
2. Gradient descent
Gradient descent is an optimization algorithm which is commonly-used to train machine learning models and neural networks.
GD algo:
3. Optimizers ?
help to faster convergence and better rates.
Ex: Momentum, RMS, Adam
they imporve the performance of training a specific model
4.1 Dropout?
droping or removing neurons at random hidden layer
when to use sigmoid fun and softmax?
sig for binary classification
softmax for multiple class classification
Greife kostenlos auf tausende geteilte Karteikarten, Zusammenfassungen, Altklausuren und mehr zu.
Jetzt loslegen
