经典必读论文推荐又来啦，这次推荐Machine learning最重要的8篇论文，统计数据来自于学术范，希望可以帮到大家~
一、ImageNet Classification with Deep Convolutional Neural Networks
作者： Alex Krizhevsky / Ilya Sutskever / Geoffrey E. Hinton
摘要:We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5%and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers,and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called “dropout”that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%,compared to 26.2% achieved by the second-best entry
全文链接:ImageNet Classification with Deep Convolutional Neural Networks——学术范
二、Deep Residual Learning for Image Recognition
作者：Kaiming He / Xiangyu Zhang / Shaoqing Ren / Jian Sun
摘要：Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, in-stead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8×deeper than VGG nets [41] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation
全文链接：Deep Residual Learning for Image Recognition——学术范
三、Scikit-learn: Machine Learning in Python
作者：Fabian Pedregosa / Ga ̈el Varoquaux / Alexandre Gramfort / Vincent Michel / Bertrand Thirion / …
摘要：Scikit-learnis a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.sourceforge.net.
全文链接：Scikit-learn: Machine Learning in Python——学术范
四、LIBSVM: A library for support vector machines
作者：Chih-Chung Chang / Chih-Jen Lin
摘要：LIBSVM is a library for Support Vector Machines (SVMs). We have been actively developing this package since the year 2000. The goal is to help users to easily apply SVM to their applications. LIBSVM has gained wide popularity in machine learning and many other areas. In this article, we present all implementation details of LIBSVM. Issues such as solving SVM optimization problems, theoretical convergence, multi-class classification, probability estimates, and parameter selection are discussed in detail.
全文链接：LIBSVM: A library for support vector machines——学术范
五、Generative Adversarial Nets
作者：Ian J. Goodfellow / Jean Pouget-Abadie / Mehdi Mirza / Bing Xu / David Warde-Farley / Sherjil Ozair / Aaron Courville / Yoshua Bengio
摘要：We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 12 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference net-works during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples
全文链接：Generative Adversarial Nets——学术范
六、Going deeper with convolutions
作者： Christian Szegedy / Wei Liu / Yangqing Jia / Pierre Sermanet / Scott Reed / Dragomir Anguelov / Dumitru Erhan / Vincent Vanhoucke / Andrew Rabinovich
摘要：We propose an efficient deep neural network architecture for computer vision, codenamed “Inception”, which derives its name from the “Network in network” paper by Lin et al in conjunction with the “we need to go deeper” internet meme. In our case, the word “deep” is used in two different meanings: first of all, in the sense that we introduce a new level of organization in the form of the “Inception module” and also in the more direct sense of increased network depth. Its design took inspiration and guidance from the theoretical work by Arora et al. The benefits of the architecture are experimentally verified on the ILSVRC 2014 classification and detection challenges, where it significantly outperforms the current state of the art while using only 1.5 billion multiply-adds for each network evaluation.
全文链接：Going deeper with convolutions——学术范
七、Dropout: A Simple Way to Prevent Neural Networks from Overfitting
作者：Nitish Srivastava / Geoffrey Hinton / Alex Krizhevsky / Ilya Sutskever / Ruslan Salakhutdinov
摘要：Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem.The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training,dropout samples from an exponential number of different “thinned” networks. At test time,it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology,obtaining state-of-the-art results on many benchmark data sets.
全文链接：Dropout: A Simple Way to Prevent Neural Networks from Overfitting——学术范
八、ImageNet Large Scale Visual Recognition Challenge
作者：Olga Russakovsky / Jia Deng / Hao Su / Jonathan Krause / Sanjeev Satheesh / Sean Ma / …
摘要：The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions.This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation,highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the five years of the challenge, and propose future directions and improvements.
全文链接：ImageNet Large Scale Visual Recognition Challenge——学术范
希望对大家有帮助！
