Skip to content
Vectorized implementation of a general feedforward neural network in Python
Branch: master
Clone or download
lgraesser
Latest commit cfe309a Sep 6, 2016
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Example1_DonutBall_CreatingDataset.ipynb Uploading neural net, datasets and code for two example applications Jul 3, 2016
Example1_DonutBall_Egs_DiffArchitectures.ipynb Adding two more sets of examples, one for each dataset Sep 2, 2016
Example1_DonutBall_NeuralNetEgs.ipynb Uploading neural net, datasets and code for two example applications Jul 3, 2016
Example2_MNIST_TestingDiffArchitectures.ipynb
Example2_MNIST_TestingLeakyRelu.ipynb
Example2_MNIST_TestingRelu.ipynb Uploading neural net, datasets and code for two example applications Jul 3, 2016
Example2_MNIST_TestingSigmoid.ipynb Uploading neural net, datasets and code for two example applications Jul 3, 2016
Example2_MNIST_best_result.ipynb
Example2_MNISTtoNumpytoPickle.ipynb Uploading neural net, datasets and code for two example applications Jul 3, 2016
MNIST_test_x.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
MNIST_test_y.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
MNIST_train_x.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
MNIST_train_y.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
NeuralNet2.ipynb Correcting typos and minor updates to comments in NeuralNet files (.p… Sep 7, 2016
NeuralNetwork.py Correcting typos and minor updates to comments in NeuralNet files (.p… Sep 7, 2016
README.md Updating README: more explanation about the files Aug 8, 2016
nn_donutballdata_test_data.pkl
nn_donutballdata_test_x.pkl
nn_donutballdata_test_y.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
nn_donutballdata_train_data.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
nn_donutballdata_train_x.pkl Uploading neural net, datasets and code for two example applications Jul 3, 2016
nn_donutballdata_train_y.pkl

README.md

A Neural Network program in Python

This is a program for a general feedforward neural network and is intended for educational purposes. It is simple and short, making it easy for a reader to quickly get into the details of how a neural network can be implemented. NeuralNet2.ipynb contains the code for the neural network, the rest of the .ipynb files are example applications, and the .pkl files are the associated data. This code accompanies a set of tutorials on neural networks, including a walkthrough of the NeuralNet2.ipynb, available at https://learningmachinelearning.org/

NeuralNetwork

NeuralNet2.ipynb is a vectorized implementation of a general feedforward neural network in Python

  • Four activation functions available: sigmoid, softmax, ReLU, and Leaky ReLU
  • Three parameter initialization functions
  • Three cost functions available: quadratic, cross entropy, log likelihood
  • Network is trained with stochastic gradient descent, variable batch size
  • L2 weight regularization available

Two example applications are provided. These demonstrate the effect of different parameter settings and network architectures on performance

  • Example1: Two class classification: Separating a ball and a donut
  • Example2: MNIST
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.