Bright Wire
https://www.jackdermody.net/brightwire
Bright Wire is an open source machine learning library for .NET with GPU supportExtending Bright Wire: Custom Activation FunctionBright Wire is designed to be easily extended. This tutorial shows how to create and use a SELU activation function that can be used to train deep feed forward neural networks along with batch normalisation.http://www.jackdermody.net/brightwire/article/Extending_Bright_Wire:_Custom_Activation_Function
http://www.jackdermody.net/brightwire/article/Extending_Bright_Wire:_Custom_Activation_Function
Convolutional Neural NetworksLearning to recognise handwritten digits (MNIST) with convolutional neural networks gives a higher classification accuracy (and a longer training time)http://www.jackdermody.net/brightwire/article/Convolutional_Neural_Networks
http://www.jackdermody.net/brightwire/article/Convolutional_Neural_Networks
Sequence to Sequence with LSTMUsing different recurrent neural network architectures for classifying sequential inputs such as one to many, many to one and sequence to sequence with Long Short Term Memory (LSTM)http://www.jackdermody.net/brightwire/article/Sequence_to_Sequence_with_LSTM
http://www.jackdermody.net/brightwire/article/Sequence_to_Sequence_with_LSTM
GRU Recurrent Neural NetworksMore complicated sequences call for more complicated neural networks. This tutorial shows how to use a GRU recurrent neural network to learn the Embedded Reber Grammar.http://www.jackdermody.net/brightwire/article/GRU_Recurrent_Neural_Networks
http://www.jackdermody.net/brightwire/article/GRU_Recurrent_Neural_Networks
Teaching a Recurrent Neural Net Binary AdditionGetting a neural net to learn the rules of binary addition and how to use its memory to store carry bits as appropriate.http://www.jackdermody.net/brightwire/article/Teaching_a_Recurrent_Neural_Net_Binary_Addition
http://www.jackdermody.net/brightwire/article/Teaching_a_Recurrent_Neural_Net_Binary_Addition
Text Clustering Four WaysFinding clusters of related documents with four different techniques - K Means, NNMF, Random Projections and SVD.http://www.jackdermody.net/brightwire/article/Text_Clustering_Four_Ways
http://www.jackdermody.net/brightwire/article/Text_Clustering_Four_Ways
Sentiment AnalysisLearning to classify sentences as containing either positive or negative sentiment with Naive Bayes and Neural Networks.http://www.jackdermody.net/brightwire/article/Sentiment_Analysis
http://www.jackdermody.net/brightwire/article/Sentiment_Analysis
Recognising Handwritten Digits (MNIST)Training a vanilla feed forward Neural Network on images of handwritten digits.http://www.jackdermody.net/brightwire/article/Recognising_Handwritten_Digits_(MNIST)
http://www.jackdermody.net/brightwire/article/Recognising_Handwritten_Digits_(MNIST)
Generating Text with Markov ChainsBuilding a Markov Model from source text and using it to generate new text.http://www.jackdermody.net/brightwire/article/Generating_Text_with_Markov_Chains
http://www.jackdermody.net/brightwire/article/Generating_Text_with_Markov_Chains
Classification Overview with Bright WireTraining Naive Bayes, Decision Tree, Random Forest, KNN, Multinomial Logistic Regression and Neural Network classifiers on the Iris data-set.http://www.jackdermody.net/brightwire/article/Classification_Overview_with_Bright_Wire
http://www.jackdermody.net/brightwire/article/Classification_Overview_with_Bright_Wire
Introduction to Bright WireProject overview and quick guide to getting started.http://www.jackdermody.net/brightwire/article/Introduction_to_Bright_Wire
http://www.jackdermody.net/brightwire/article/Introduction_to_Bright_Wire