TargetIt / digitsRecognizer

record different positions digit recognition for ML and DL

digitsRecognizer

• there are three folders under digitsRecognizer.
• example is used to store classical ML and DL digits recognition examples from network.
• lab records my lab during learning example
• report records my notes and summary for ML and DL

example

• machineLearningInAction https://github.com/pbharrin/machinelearninginaction https://www.manning.com/books/machine-learning-in-action machine learning in action KNN SVM
• nn-from-scratch http://www.wildml.com/2015/09/implementing-a-neural-network-from-scratch/ https://github.com/dennybritz/nn-from-scratch
• neural-networks-and-deep-learning-master http://neuralnetworksanddeeplearning.com/
• tensorflow https://github.com/tensorflow/tensorflow https://www.tensorflow.org/ softmax CNN
• keras https://keras.io/ https://github.com/fchollet/keras
• handson-ml https://github.com/ageron/handson-ml multiclassification RNN
• kaggle https://www.kaggle.com/
• skLearn http://scikit-learn.org/stable/ https://github.com/scikit-learn/scikit-learn

lab

lab.ml
	machine learning
lab.dl
	deep learning
lab.tf
	tensorflow

report

make your own neural network
	https://github.com/makeyourownneuralnetwork/makeyourownneuralnetwork
Fully connected network
CNN convolution
RNN LSTM
Gradient descent

Reference

http://cs231n.stanford.edu/
http://colah.github.io/
http://neuralnetworksanddeeplearning.com/
Deep Learning Tutorial by Huang-yi Lee