Difference between revisions of "Orange: Neural Network"

From OnnoWiki
Jump to navigation Jump to search
 
(7 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
Sumber:https://docs.biolab.si//3/visual-programming/widgets/model/neuralnetwork.html
 
Sumber:https://docs.biolab.si//3/visual-programming/widgets/model/neuralnetwork.html
  
A multi-layer perceptron (MLP) algorithm with backpropagation.
+
Widget Neural Network sebuah multi-layer perceptron (MLP) algorithm dengan backpropagation.
  
Inputs
+
==Input==
  
    Data: input dataset
+
Data: input dataset
    Preprocessor: preprocessing method(s)
+
Preprocessor: preprocessing method(s)
  
Outputs
+
==Output==
  
    Learner: multi-layer perceptron learning algorithm
+
Learner: multi-layer perceptron learning algorithm
    Model: trained model
+
Model: trained model
  
The Neural Network widget uses sklearn’s Multi-layer Perceptron algorithm that can learn non-linear models as well as linear.
+
Widget Neural Network menggunakan sklearn Multi-layer Perceptron algorithm yang dapat learn non-linear maupun linear model. Kita bisa mengatur activatio function yang digunakan (default ReLu), jumlah Neuron per hidden layer Solver yang digunakan (default Adam) dll.
  
[[File:NeuralNetwork-stamped.png|center|200px|thumb]]
+
[[File:NeuralNetwork-stamped.png|center|300px|thumb]]
  
    A name under which it will appear in other widgets. The default name is “Neural Network”.
+
* A name under which it will appear in other widgets. The default name is “Neural Network”.
    Set model parameters:
+
* Set model parameters:
        Neurons per hidden layer: defined as the ith element represents the number of neurons in the ith hidden layer. E.g. a neural network with 3 layers can be defined as 2, 3, 2.
+
 
        Activation function for the hidden layer:
+
** Neurons per hidden layer: defined as the ith element represents the number of neurons in the ith hidden layer. E.g. a neural network with 3 layers can be defined as 2, 3, 2.
            Identity: no-op activation, useful to implement linear bottleneck
+
** Activation function for the hidden layer:
            Logistic: the logistic sigmoid function
+
*** Identity: no-op activation, useful to implement linear bottleneck
            tanh: the hyperbolic tan function
+
*** Logistic: the logistic sigmoid function
            ReLu: the rectified linear unit function
+
*** tanh: the hyperbolic tan function
        Solver for weight optimization:
+
*** ReLu: the rectified linear unit function
            L-BFGS-B: an optimizer in the family of quasi-Newton methods
+
 
            SGD: stochastic gradient descent
+
** Solver for weight optimization:
            Adam: stochastic gradient-based optimizer
+
*** L-BFGS-B: an optimizer in the family of quasi-Newton methods
        Alpha: L2 penalty (regularization term) parameter
+
*** SGD: stochastic gradient descent
        Max iterations: maximum number of iterations
+
*** Adam: stochastic gradient-based optimizer
    Other parameters are set to sklearn’s defaults.
+
 
    Produce a report.
+
** Alpha: L2 penalty (regularization term) parameter
    When the box is ticked (Apply Automatically), the widget will communicate changes automatically. Alternatively, click Apply.
+
** Max iterations: maximum number of iterations
 +
 
 +
* Other parameters are set to sklearn’s defaults.
 +
* Produce a report.
 +
* When the box is ticked (Apply Automatically), the widget will communicate changes automatically. Alternatively, click Apply.
  
 
==Contoh==
 
==Contoh==
  
The first example is a classification task on iris dataset. We compare the results of Neural Network with the Logistic Regression.
+
Contoh berikut adalah task classification pada iris dataset. Kita membandingkan hasil dari widget Neural Network dengan widget Logistic Regression.
  
[[File:NN-Example-Test.png|center|200px|thumb]]
+
[[File:NN-Example-Test.png|center|600px|thumb]]
  
The second example is a prediction task, still using the iris data. This workflow shows how to use the Learner output. We input the Neural Network prediction model into Predictions and observe the predicted values.
+
Contoh berikut adalah task prediction, menggunakan iris data. Workflow ini memperlihatkan bagaimana cara menggunakan keluaran Learner. Kita memasukan widget Neural Network prediction model ke widget Predictions dan mengamati nilai hasil prediksi.
 
 
[[File:NN-Example-Predict.png|center|200px|thumb]]
 
  
 +
[[File:NN-Example-Predict.png|center|600px|thumb]]
  
 
Contoh WorkFlow lainnya,
 
Contoh WorkFlow lainnya,
Line 51: Line 54:
 
[[File:Orange-NN.png|center|400px|thumb]]
 
[[File:Orange-NN.png|center|400px|thumb]]
  
 +
==Youtube==
 +
 +
* [https://www.youtube.com/watch?v=I6OrCwZE47o YOUTUBE: ORANGE neural network]
  
 
==Referensi==
 
==Referensi==

Latest revision as of 05:01, 9 April 2020

Sumber:https://docs.biolab.si//3/visual-programming/widgets/model/neuralnetwork.html

Widget Neural Network sebuah multi-layer perceptron (MLP) algorithm dengan backpropagation.

Input

Data: input dataset
Preprocessor: preprocessing method(s)

Output

Learner: multi-layer perceptron learning algorithm
Model: trained model

Widget Neural Network menggunakan sklearn Multi-layer Perceptron algorithm yang dapat learn non-linear maupun linear model. Kita bisa mengatur activatio function yang digunakan (default ReLu), jumlah Neuron per hidden layer Solver yang digunakan (default Adam) dll.

NeuralNetwork-stamped.png
  • A name under which it will appear in other widgets. The default name is “Neural Network”.
  • Set model parameters:
    • Neurons per hidden layer: defined as the ith element represents the number of neurons in the ith hidden layer. E.g. a neural network with 3 layers can be defined as 2, 3, 2.
    • Activation function for the hidden layer:
      • Identity: no-op activation, useful to implement linear bottleneck
      • Logistic: the logistic sigmoid function
      • tanh: the hyperbolic tan function
      • ReLu: the rectified linear unit function
    • Solver for weight optimization:
      • L-BFGS-B: an optimizer in the family of quasi-Newton methods
      • SGD: stochastic gradient descent
      • Adam: stochastic gradient-based optimizer
    • Alpha: L2 penalty (regularization term) parameter
    • Max iterations: maximum number of iterations
  • Other parameters are set to sklearn’s defaults.
  • Produce a report.
  • When the box is ticked (Apply Automatically), the widget will communicate changes automatically. Alternatively, click Apply.

Contoh

Contoh berikut adalah task classification pada iris dataset. Kita membandingkan hasil dari widget Neural Network dengan widget Logistic Regression.

NN-Example-Test.png

Contoh berikut adalah task prediction, menggunakan iris data. Workflow ini memperlihatkan bagaimana cara menggunakan keluaran Learner. Kita memasukan widget Neural Network prediction model ke widget Predictions dan mengamati nilai hasil prediksi.

NN-Example-Predict.png

Contoh WorkFlow lainnya,


Orange-NN.png

Youtube

Referensi

Pranala Menarik