06 neurolab python
Download as PPTX, PDF1 like1,842 views
Neurolab is a Python library designed for developing neural networks with a user-friendly interface similar to MATLAB's neural network toolbox. It supports various types of neural networks including single-layer perceptrons, multilayer perceptrons, and recurrent networks, with flexible configurations and learning algorithms. Installation can be done via pip or setuptools, and the library utilizes NumPy and SciPy for enhanced functionality.
![Example
• To Create network with 2 inputs and 10 neurons
• each input values are between -1 and 1
>>> net = newp([[-1, 1], [-1, 1]], 10)
8](https://image.slidesharecdn.com/06neurolabpython-180320105238/85/06-neurolab-python-8-320.jpg)
![Example
• create neural net with 2 inputs
• input range for each input is [-0.5, 0.5]
• 3 neurons for hidden layer, 1 neuron for output
• 2 layers including hidden layer and output layer
>>> net = newff( [[-0.5, 0.5], [-0.5, 0.5]] , [3, 1])
>>> net.ci
2
>>> net.co
1
>>> len(net.layers)
2
13](https://image.slidesharecdn.com/06neurolabpython-180320105238/85/06-neurolab-python-13-320.jpg)
06 neurolab python
- 1. Neural Networks and Fuzzy Systems NeuroLab (a simple and powerful Neural Network Library for Python) Dr. Tamer Ahmed Farrag Course No.: 803522-3
- 2. NeuroLab 0.3.5 • NeuroLab - a library of basic neural networks algorithms with flexible network configurations and learning algorithms for Python. To simplify the using of the library, interface is similar to the package of Neural Network Toolbox (NNT) of MATLAB© . • The library is based on the package numpy (http://numpy.scipy.org), some learning algorithms are used scipy.optimize (http://scipy.org). 2
- 3. Features • Pure python + numpy • API like Neural Network Toolbox (NNT) from MATLAB • Interface to use train algorithms form scipy.optimize • Flexible network configurations and learning algorithms. You may change: train, error, initialization and activation functions • Unlimited number of neural layers and number of neurons in layers • Variety of supported types of Artificial Neural Network and learning algorithms 3
- 4. Supported neural networks types 4 • Single layer perceptron • Multilayer feed forward perceptron • Competing layer (Kohonen Layer) • Learning Vector Quantization (LVQ) • Elman Recurrent network • Hopfield Recurrent network • Hemming Recurrent network
- 5. Install 5 • Open Anconda Prompt as administrator as shown • Install neurolab using setuptools/distribute: easy_install neurolab • Or pip: pip install neurolab
- 6. net: Neural Networks 6 Network Type Function Count of layers Support train fcn Error fcn Single-layer perceptron newp 1 train_delta SSE Multi-layer perceptron newff >=1 train_gd, train_gdm, train_gda, train_gdx, train_rprop, train_bfgs*, train_cg SSE Competitive layer newc 1 train_wta, train_cwta* SAE LVQ newlvq 2 train_lvq MSE Elman newelm >=1 train_gdx MSE Hopield newhop 1 None None Hemming newhem 2 None None • The module contains the basic network architectures
- 7. Single Layer Perceptron (newp) 7 • Syntax: neurolab.net.newp(minmax, cn, transf=<neurolab.trans.HardLim>) • Parameters: • minmax: list of list, the outer list is the number of input neurons, inner lists must contain 2 elements: min and maxRange of each input values • cn: int, number of output neurons Number of neurons • transf: func (default HardLim) Activation function • Returns: • net: Net
- 8. Example • To Create network with 2 inputs and 10 neurons • each input values are between -1 and 1 >>> net = newp([[-1, 1], [-1, 1]], 10) 8
- 9. 9
- 10. 10
- 11. 11
- 12. • Syntax: neurolab.net.newff(minmax, size, transf=None) Parameters: • minmax: list of list, the outer list is the number of input neurons, inner lists must contain 2 elements: min and max Range of each input values • size: the length of list equal to the number of layers except input layer, the element of the list is the neuron number for corresponding layer Contains the number of neurons for each layer • transf: list (default TanSig) List of activation function for each layer • Returns: • net: Net Feed Forward Multilayer Perceptron (newff) 12
- 13. Example • create neural net with 2 inputs • input range for each input is [-0.5, 0.5] • 3 neurons for hidden layer, 1 neuron for output • 2 layers including hidden layer and output layer >>> net = newff( [[-0.5, 0.5], [-0.5, 0.5]] , [3, 1]) >>> net.ci 2 >>> net.co 1 >>> len(net.layers) 2 13
- 14. 14
- 15. 15
- 16. 16
- 17. Resources • NeuroLab web site: https://pythonhosted.org/neurolab/index.html • Library: https://pythonhosted.org/neurolab/lib.html# • Examples: https://pythonhosted.org/neurolab/example.html 17