Orange: Neural Network - Revision history

Onnowpurbo: /* Referensi */

2020-04-08T22:01:58Z

Referensi

← Older revision		Revision as of 22:01, 8 April 2020
Line 53:		Line 53:

	[[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==

Onnowpurbo: /* Contoh */

2020-04-06T03:28:22Z

Contoh

← Older revision		Revision as of 03:28, 6 April 2020
Line 43:		Line 43:
	Contoh berikut adalah task classification pada iris dataset. Kita membandingkan hasil dari widget Neural Network dengan widget 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]]

	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.		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 53:		Line 53:

	[[File:Orange-NN.png\|center\|400px\|thumb]]		[[File:Orange-NN.png\|center\|400px\|thumb]]


	==Referensi==		==Referensi==

Onnowpurbo: /* Output */

2020-04-06T03:28:07Z

Output

← Older revision		Revision as of 03:28, 6 April 2020
Line 15:		Line 15:
	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.		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”.

Onnowpurbo: /* Output */

2020-04-06T03:26:51Z

Output

← Older revision		Revision as of 03:26, 6 April 2020
Line 13:		Line 13:
	Model: trained model		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 dll.		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\|200px\|thumb]]

Onnowpurbo: /* Output */

2020-04-06T03:26:31Z

Output

← Older revision		Revision as of 03:26, 6 April 2020
Line 13:		Line 13:
	Model: trained model		Model: trained model

	Widget Neural Network menggunakan sklearn Multi-layer Perceptron algorithm yang dapat learn non-linear maupun linear 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 dll.

	[[File:NeuralNetwork-stamped.png\|center\|200px\|thumb]]		[[File:NeuralNetwork-stamped.png\|center\|200px\|thumb]]

Onnowpurbo at 11:18, 5 April 2020

2020-04-05T11:18:53Z

← Older revision		Revision as of 11:18, 5 April 2020
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

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

	==Input==		==Input==
Line 41:		Line 41:
	==Contoh==		==Contoh==

	Contoh ~~pertama~~ adalah task classification pada iris dataset. Kita membandingkan hasil dari Neural Network dengan 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\|200px\|thumb]]

	Contoh ~~ke dua~~ adalah task prediction, menggunakan iris data. Workflow ini memperlihatkan bagaimana cara menggunakan keluaran Learner. Kita memasukan Neural Network prediction model ke widget Predictions dan mengamati nilai hasil prediksi.		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\|200px\|thumb]]

Onnowpurbo at 21:31, 6 March 2020

2020-03-06T21:31:07Z

← Older revision		Revision as of 21:31, 6 March 2020
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.		Sebuah multi-layer perceptron (MLP) algorithm dengan backpropagation.

	==Input==		==Input==
Line 13:		Line 13:
	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.

	[[File:NeuralNetwork-stamped.png\|center\|200px\|thumb]]		[[File:NeuralNetwork-stamped.png\|center\|200px\|thumb]]
Line 41:		Line 41:
	==Contoh==		==Contoh==

	~~The first example is a~~ classification ~~task on~~ iris dataset. ~~We compare the results of~~ Neural Network ~~with the~~ Logistic Regression.		Contoh pertama adalah task classification pada iris dataset. Kita membandingkan hasil dari Neural Network dengan Logistic Regression.

	[[File:NN-Example-Test.png\|center\|200px\|thumb]]		[[File:NN-Example-Test.png\|center\|200px\|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 ke dua adalah task prediction, menggunakan iris data. Workflow ini memperlihatkan bagaimana cara menggunakan keluaran Learner. Kita memasukan 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\|200px\|thumb]]

Onnowpurbo at 04:12, 28 January 2020

2020-01-28T04:12:26Z

← Older revision		Revision as of 04:12, 28 January 2020
Line 3:		Line 3:
	A multi-layer perceptron (MLP) algorithm with backpropagation.		A multi-layer perceptron (MLP) algorithm with 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.		The Neural Network widget uses sklearn’s Multi-layer Perceptron algorithm that can learn non-linear models as well as linear.
Line 17:		Line 17:
	[[File:NeuralNetwork-stamped.png\|center\|200px\|thumb]]		[[File:NeuralNetwork-stamped.png\|center\|200px\|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==
Line 44:		Line 48:

	[[File:NN-Example-Predict.png\|center\|200px\|thumb]]		[[File:NN-Example-Predict.png\|center\|200px\|thumb]]


	Contoh WorkFlow lainnya,		Contoh WorkFlow lainnya,

Onnowpurbo at 03:05, 23 January 2020

2020-01-23T03:05:10Z

Onnowpurbo at 07:09, 16 January 2020

2020-01-16T07:09:31Z

← Older revision		Revision as of 07:09, 16 January 2020
Line 1:		Line 1:
			Sumber:https://docs.biolab.si//3/visual-programming/widgets/model/neuralnetwork.html

			A multi-layer perceptron (MLP) algorithm with backpropagation.

			Inputs

			Data: input dataset

			Preprocessor: preprocessing method(s)

			Outputs

			Learner: multi-layer perceptron learning algorithm

			Model: trained model

			The Neural Network widget uses sklearn’s Multi-layer Perceptron algorithm that can learn non-linear models as well as linear.

			../../_images/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.

			Examples

			The first example is a classification task on iris dataset. We compare the results of Neural Network with the Logistic Regression.

			../../_images/NN-Example-Test.png

			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.

			../../_images/NN-Example-Predict.png




	[[File:Orange-NN.png\|center\|400px\|thumb]]		[[File:Orange-NN.png\|center\|400px\|thumb]]


			==Referensi==

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

			==Pranala Menarik==

			* [[Orange]]

← Older revision		Revision as of 03:05, 23 January 2020
Line 6:		Line 6:

	Data: input dataset		Data: input dataset

	Preprocessor: preprocessing method(s)		Preprocessor: preprocessing method(s)

Line 12:		Line 11:

	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.		The Neural Network widget uses sklearn’s Multi-layer Perceptron algorithm that can learn non-linear models as well as linear.

	~~../../_images/~~NeuralNetwork-stamped.png		[[File:NeuralNetwork-stamped.png\|center\|200px\|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.		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:		Activation function for the hidden layer:

	Identity: no-op activation, useful to implement linear bottleneck		Identity: no-op activation, useful to implement linear bottleneck

	Logistic: the logistic sigmoid function		Logistic: the logistic sigmoid function

	tanh: the hyperbolic tan function		tanh: the hyperbolic tan function

	ReLu: the rectified linear unit function		ReLu: the rectified linear unit function

	Solver for weight optimization:		Solver for weight optimization:

	L-BFGS-B: an optimizer in the family of quasi-Newton methods		L-BFGS-B: an optimizer in the family of quasi-Newton methods

	SGD: stochastic gradient descent		SGD: stochastic gradient descent

	Adam: stochastic gradient-based optimizer		Adam: stochastic gradient-based optimizer

	Alpha: L2 penalty (regularization term) parameter		Alpha: L2 penalty (regularization term) parameter

	Max iterations: maximum number of iterations		Max iterations: maximum number of iterations

	Other parameters are set to sklearn’s defaults.		Other parameters are set to sklearn’s defaults.

	Produce a report.		Produce a report.

	When the box is ticked (Apply Automatically), the widget will communicate changes automatically. Alternatively, click Apply.		When the box is ticked (Apply Automatically), the widget will communicate changes automatically. Alternatively, click Apply.

	~~Examples~~		==Contoh==

	The first example is a classification task on iris dataset. We compare the results of Neural Network with the Logistic Regression.		The first example is a classification task on iris dataset. We compare the results of Neural Network with the Logistic Regression.

	~~../../_images/~~NN-Example-Test.png		[[File:NN-Example-Test.png\|center\|200px\|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.		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.

	~~../../_images/~~NN-Example-Predict.png		[[File:NN-Example-Predict.png\|center\|200px\|thumb]]


			Contoh WorkFlow lainnya,