Deep Learning Notes
Deep learning (deep structured learning, hierarchical learning or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers, with complex structures or otherwise, composed of multiple non-linear transformations.
This document summarizes two years of collected notes in deep learning society including Stanford opensource materials by Professor Andrew Ng as well as advanced machine learnings notes from Columbia University.
– Logistic Regression as Neural Network
– Shallow Neural Network
– Deep Neural Network
– DNN: Hypter-parameter tuning, regularization and optimization
– Convolutional Neural Network
– CNN: Pooling Layers, LeNet5, AlexNet, VGG-16, and ResNet
– Natural Language Processing
– NLP: Recurrent Neural Network
– Gated Recurrent Unit
– Long Short Term Memory
– Bidirectional RNNs