- Notifications
You must be signed in to change notification settings - Fork51
Implementation of Artificial Neural Networks using NumPy
ahmedfgad/NumPyANN
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
NumPyANN is a Python project for building artificial neural networks using NumPy.
NumPyANN is part ofPyGAD which is an open-source Python 3 library for implementing the genetic algorithm and optimizing machine learning algorithms. Both regression and classification neural networks are supported starting from PyGAD 2.7.0.
Check documentation of theNeuralGenetic project in the PyGAD's documentation:https://pygad.readthedocs.io/en/latest/nn.html
The library is under active development and more features are added regularly. If you want a feature to be supported, please check theContact Us section to send a request.
- Credit/Debit Card:https://donate.stripe.com/eVa5kO866elKgM0144
- Open Collective:opencollective.com/pygad
- PayPal: Use either this link:paypal.me/ahmedfgad or the e-mail addressahmed.f.gad@gmail.com
- Interac e-Transfer: Use e-mail addressahmed.f.gad@gmail.com
IMPORTANT If you are coming for the code of the tutorial titledArtificial Neural Network Implementation using NumPy and Classification of the Fruits360 Image Dataset, then it has been moved to theTutorialProject directory on 10 May 2020.
To installPyGAD, simply use pip to download and install the library fromPyPI (Python Package Index). The library is at PyPI at this pagehttps://pypi.org/project/pygad.
Install PyGAD with the following command:
pipinstallpygad
To get started with PyGAD, please read the documentation atRead The Docshttps://pygad.readthedocs.io.
The source code of the PyGAD' modules is found in the following GitHub projects:
- pygad: (https://github.com/ahmedfgad/GeneticAlgorithmPython)
- pygad.nn:https://github.com/ahmedfgad/NumPyANN
- pygad.gann:https://github.com/ahmedfgad/NeuralGenetic
- pygad.cnn:https://github.com/ahmedfgad/NumPyCNN
- pygad.gacnn:https://github.com/ahmedfgad/CNNGenetic
- pygad.kerasga:https://github.com/ahmedfgad/KerasGA
- pygad.torchga:https://github.com/ahmedfgad/TorchGA
The documentation of PyGAD is available atRead The Docshttps://pygad.readthedocs.io.
The documentation of the PyGAD library is available atRead The Docs at this link:https://pygad.readthedocs.io. It discusses the modules supported by PyGAD, all its classes, methods, attribute, and functions. For each module, a number of examples are given.
If there is an issue using PyGAD, feel free to post at issue in thisGitHub repositoryhttps://github.com/ahmedfgad/GeneticAlgorithmPython or by sending an e-mail toahmed.f.gad@gmail.com.
If you built a project that uses PyGAD, then please drop an e-mail toahmed.f.gad@gmail.com with the following information so that your project is included in the documentation.
- Project title
- Brief description
- Preferably, a link that directs the readers to your project
Please check theContact Us section for more contact details.
The next figure lists the different stages in the lifecycle of an instance of thepygad.GA class. Note that PyGAD stops when either all generations are completed or when the function passed to theon_generation parameter returns the stringstop.
The next code implements all the callback functions to trace the execution of the genetic algorithm. Each callback function prints its name.
importpygadimportnumpyfunction_inputs= [4,-2,3.5,5,-11,-4.7]desired_output=44deffitness_func(ga_instance,solution,solution_idx):output=numpy.sum(solution*function_inputs)fitness=1.0/ (numpy.abs(output-desired_output)+0.000001)returnfitnessfitness_function=fitness_funcdefon_start(ga_instance):print("on_start()")defon_fitness(ga_instance,population_fitness):print("on_fitness()")defon_parents(ga_instance,selected_parents):print("on_parents()")defon_crossover(ga_instance,offspring_crossover):print("on_crossover()")defon_mutation(ga_instance,offspring_mutation):print("on_mutation()")defon_generation(ga_instance):print("on_generation()")defon_stop(ga_instance,last_population_fitness):print("on_stop()")ga_instance=pygad.GA(num_generations=3,num_parents_mating=5,fitness_func=fitness_function,sol_per_pop=10,num_genes=len(function_inputs),on_start=on_start,on_fitness=on_fitness,on_parents=on_parents,on_crossover=on_crossover,on_mutation=on_mutation,on_generation=on_generation,on_stop=on_stop)ga_instance.run()
Based on the used 3 generations as assigned to thenum_generations argument, here is the output.
on_start()on_fitness()on_parents()on_crossover()on_mutation()on_generation()on_fitness()on_parents()on_crossover()on_mutation()on_generation()on_fitness()on_parents()on_crossover()on_mutation()on_generation()on_stop()Check thePyGAD's documentation for information about the implementation of this example.
importnumpyimportpygad.nn# Preparing the NumPy array of the inputs.data_inputs=numpy.array([[1,1], [1,0], [0,1], [0,0]])# Preparing the NumPy array of the outputs.data_outputs=numpy.array([0,1,1,0])# The number of inputs (i.e. feature vector length) per samplenum_inputs=data_inputs.shape[1]# Number of outputs per samplenum_outputs=2HL1_neurons=2# Building the network architecture.input_layer=pygad.nn.InputLayer(num_inputs)hidden_layer1=pygad.nn.DenseLayer(num_neurons=HL1_neurons,previous_layer=input_layer,activation_function="relu")output_layer=pygad.nn.DenseLayer(num_neurons=num_outputs,previous_layer=hidden_layer1,activation_function="softmax")# Training the network.pygad.nn.train(num_epochs=10,last_layer=output_layer,data_inputs=data_inputs,data_outputs=data_outputs,learning_rate=0.01)# Using the trained network for predictions.predictions=pygad.nn.predict(last_layer=output_layer,data_inputs=data_inputs)# Calculating some statisticsnum_wrong=numpy.where(predictions!=data_outputs)[0]num_correct=data_outputs.size-num_wrong.sizeaccuracy=100* (num_correct/data_outputs.size)print("Number of correct classifications : {num_correct}.".format(num_correct=num_correct))print("Number of wrong classifications : {num_wrong}.".format(num_wrong=num_wrong.size))print("Classification accuracy : {accuracy}.".format(accuracy=accuracy))
There are different resources that can be used to get started with the genetic algorithm and building it in Python.
To start with coding the genetic algorithm, you can check the tutorial titledGenetic Algorithm Implementation in Python available at these links:
This tutorial is prepared based on a previous version of the project but it still a good resource to start with coding the genetic algorithm.
Get started with the genetic algorithm by reading the tutorial titledIntroduction to Optimization with Genetic Algorithm which is available at these links:
Read about building neural networks in Python through the tutorial titledArtificial Neural Network Implementation using NumPy and Classification of the Fruits360 Image Dataset available at these links:
Read about training neural networks using the genetic algorithm through the tutorial titledArtificial Neural Networks Optimization using Genetic Algorithm with Python available at these links:
To start with coding the genetic algorithm, you can check the tutorial titledBuilding Convolutional Neural Network using NumPy from Scratch available at these links:
This tutorial) is prepared based on a previous version of the project but it still a good resource to start with coding CNNs.
Get started with the genetic algorithm by reading the tutorial titledDerivation of Convolutional Neural Network from Fully Connected Network Step-By-Step which is available at these links:
You can also check my book cited asAhmed Fawzy Gad 'Practical Computer Vision Applications Using Deep Learning with CNNs'. Dec. 2018, Apress, 978-1-4842-4167-7 which discusses neural networks, convolutional neural networks, deep learning, genetic algorithm, and more.
Find the book at these links:
If you used PyGAD, please consider adding a citation to the following paper about PyGAD:
@misc{gad2021pygad, title={PyGAD: An Intuitive Genetic Algorithm Python Library}, author={Ahmed Fawzy Gad}, year={2021}, eprint={2106.06158}, archivePrefix={arXiv}, primaryClass={cs.NE}}