Machine Learning & Deep Learning 论文阅读笔记

Papers

My Machine Learning & Deep Learning Papers Notes.

Contents

Machine Learning

• Distance-based features in pattern classification (2011) (feature engineering)
• A Few Useful Things to Know about Machine Learning (2012) (basic ml concepts)

Deep Learning

• Understanding the difficulty of training deep feedforward neural networks (2010)
• On the importance of initialization and momentum in deep learning (2013)
• Accelerating learning via knowledge transfer (2016)(Net2net)

Computer Vision

• ImageNet classification with deep convolutional neural networks (2012) (AlexNet, Deep Learning Breakthrough)
• Maxout networks (2013.02) (new activation function approximate any convex function)
• Network In Network (2013.12) (micro networks approximate any function)
• Very deep convolutional networks for large-scale image recognition (2014.09) (VGGNet, become very deep)
• Return of the devil in the details: delving deep into convolutional nets (2014.05)
• Going deeper with convolutions (2014.09) (GoogLeNet, Inception-v1)
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (2015.02) (Inception-v2)
• Rethinking the Inception Architecture for Computer Vision (2015.12) (Inception-v3)
• Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016.02) (Inception-v4, Inception-ResNet)
• Training Very Deep Networks (2015.07) (Highway Networks)
• Recurrent Highway Networks (2016.07)
• Highway and Residual Networks learn Unrolled Iterative Estimation (2016.12)
• Deep residual learning for image recognition (2015.12) (ResNet-v1)
• Identity Mappings in Deep Residual Networks (2016.03) (ResNet-v2)
• Wide Residual Networks (2016.05)(more kernels in residual blocks, widen k times)
• Deep Networks with Stochastic Depth (2016.03)
• FractalNet: Ultra-Depp neural networks without residuals (2016.05)
• Residual Networks of Residual Networks: Multilevel Residual Networks (2016.08)(RoR, residual mapping of residual mapping)
• Densely Connected Convolutional Networks (2016.08)
• Aggregated Residual Transformations for Deep Neural Networks (2016.11) (ResNet-v3, ResNeXt)

Natural Language Processing

• A Primer on Neural Network Models for Natural Language Processing
• Natural Language Processing (Almost) from Scratch
• Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing (2012)
• Distributed representations of words and phrases and their compositionality (2013)(word2vec)
• Efficient estimation of word representations in vector space (2013)
• Distributed representations of sentences and documents (2014)
• Glove: Global vectors for word representation (2014)
• Convolutional neural networks for sentence classification (2014)
• A convolutional neural network for modeling sentences (2014)
• Recursive deep models for semantic compositionality over a sentiment treebank (2013)
• Sequence to sequence learning with neural networks (2014)
• Generating sequences with recurrent neural networks (2013)(LSTM, very nice generating result, show the power of RNN)
• Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014)
• Sequence to sequence learning with neural networks (2014)(Outstanding Work)
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing (2015)
• Character-Aware Neural Language Models (2015)
• Teaching Machines to Read and Comprehend (2015)(CNN/DailyMail cloze style questions)
• Very Deep Convolutional Networks for Natural Language Processing (2016)(state-of-the-art in text classification)
• Bag of Tricks for Efficient Text Classification (2016)(slightly worse than state-of-the-art, but a lot faster)

License

This project is licensed under the terms of the MIT license.

完整项目工程见 github：Machine Learning & Deep Learning Paper Notes，持续更新，欢迎大家一起研读论文。