10 Best machine learning papers

10 Best ever machine learning research paper

Artificial Intelligence:

Artificial intelligence (AI) is an area of computer science that emphasizes the creation of machines having intelligence that work and react like humans. AI is designed to have the most predominant capabilities that humans equipped with like-

  • Reasoning
  • Speech
  • Vision

AI is accomplished by studying how the human brain thinks, and how humans learn, decide, and work while trying to solve a problem. Using the outcomes of this study as a basis for developing intelligent software and systems. Knowledge engineering is a core of this whole AI. If a machine has abundant information relating to the world and has the processing power to process this information. Then a machine can often act & react like humans. So Perception and interception of the knowledge(Data) make the machine intelligent.


Want to know more artificial this article surely help you Artificial Intelligence Introduction


The way artificial intelligence gaining popularity, A huge amount of research work is done. Most Gaint companies like..

  • Google
  • Facebook
  • Microsoft
  • IBM
  • Apple
  • Alibaba
  • ..(more)

are investing hugely in AI research.

If you go for research papers on artificial intelligence it’s like huge. On a daily basis, A new research paper came with a new glorifying idea. But very few gain popularity “Here I am gonna talk about 10 most impressive Research Papers around Artificial Intelligence

Selection Criteria

Most of these papers have been chosen on the basis of citation value for each. Some of these papers take into account a Highly Influential Citation count (HIC) and Citation Velocity (CV).

Citation Value: To manually calculate your h-index, organize articles in descending order, based on the number of times they have been cited. Web of Science, Scopus, and Google Scholar can also be used to calculate an h-index for that particular citation-tracking database.

Citation Velocity: is the weighted average number of citations per year over the last 3 years.

10 Best machine learning papers from(2014-2018)

Paper 1:

Dropout: a simple way to prevent neural networks from overfitting, by G.Hinton, G.E., Krizhevsky, A., Srivastava, N., Sutskever, I., & Salakhutdinov, R. (2014). Journal of Machine Learning Research, 15, 1929-1958. (cited 2084 times, HIC: 142, CV: 536).

Dropout

This research paper somehow solves the problem of overfitting.

Summary: 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. This significantly reduces overfitting and gives major improvements over other regularization methods.

Paper 2:

Deep Residual Learning for Image Recognition, by He, K., Ren, S., Sun, J., & Zhang, X. (2016). CoRR, abs/1512.03385. (cited 1436 times, HIC: 137, CV: 582).

Summary: We present a residual learning framework to ease the training of deep neural networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead 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.

Paper 3:

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, by Sergey Ioffe, Christian Szegedy (2015) ICML. (cited 946 times, HIC: 56 , CV: 0).

Batch Normalization fastened the process of training the model and helps to achieve accuracy in less training steps, “Fewer epochs.”

Summary: Training Deep Neural Networks is complicated by the fact that the distribution of each layer’s inputs changes during training, as the parameters of the previous layers change. We refer to this phenomenon as an internal covariate shift and address the problem by normalizing layer inputs. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps and beats the original model by a significant margin.

Paper 4:

Large-Scale Video Classification with Convolutional Neural Networks, by Fei-Fei, L., Karpathy, A., Leung, T., Shetty, S., Sukthankar, R., & Toderici, G. (2014). IEEE Conference on Computer Vision and Pattern Recognition (cited 865 times, HIC: 24, CV: 239)

CNN

After Alex net (for image classification) in 2012, there is a lot of work is going on video classification and then this paper came, it changes the whole scenario. Leads to the classification of objects detection in live streaming.

Summary: Convolutional Neural Networks (CNN) has been established as a powerful class of models for image recognition problems. Encouraged by these results, we provide an extensive empirical evaluation of CNN’s on large-scale video classification using a new dataset of 1 million YouTube videos belonging to 487 classes.

Paper 5:

Microsoft COCO: Common Objects in Context, by Belongie, S.J., Dollár, P., Hays, J., Lin, T., Maire, M., Perona, P., Ramanan, D., & Zitnick, C.L. (2014). ECCV. (cited 830 times, HIC: 78, CV: 279)

Summary: We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4-year-old. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

Paper 6:

Learning deep features for scene recognition using places database, by Lapedriza, À., Oliva, A., Torralba, A., Xiao, J., & Zhou, B. (2014). NIPS. (cited 644 times, HIC: 65 , CV: 0)
Summary: We introduce a new scene-centric database called Places with over 7 million labeled pictures of scenes. We propose new methods to compare the density and diversity of image datasets and show that Places is as dense as other scene datasets and has more diversity.

Paper 7:

Generative adversarial nets, by Bengio, Y., Courville, A.C., Goodfellow, I.J., Mirza, M., Ozair, S., Pouget-Abadie, J., Warde-Farley, D., & Xu, B. (2014) NIPS. (cited 463 times, HIC: 55 , CV: 0)

Most popular one & my favorite one.

Summary: 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.

Paper 8:

How transferable are features in deep neural networks, by Bengio, Y., Clune, J., Lipson, H., & Yosinski, J. (2014) CoRR, abs/1411.1792. (cited 402 times, HIC: 14 , CV: 0)

Summary: We experimentally quantify the generality versus specificity of neurons in each layer of a deep convolutional neural network and report a few surprising results. Transferability is negatively affected by two distinct issues: (1) the specialization of higher layer neurons to their original task at the expense of performance on the target task, which was expected, and (2) optimization difficulties related to splitting networks between co-adapted neurons, which was not expected.

Paper 9:

Multi-scale Orderless Pooling of Deep Convolutional Activation Features, by Gong, Y., Guo, R., Lazebnik, S., & Wang, L. (2014). ECCV(cited 293 times, HIC: 23 , CV: 95)

Summary: To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN).

Paper 10:

How transferable are features in deep neural networks, by Bengio, Y., Clune, J., Lipson, H., & Yosinski, J. (2014) CoRR, abs/1411.1792. (cited 402 times, HIC: 14 , CV: 0)

Summary: We experimentally quantify the generality versus specificity of neurons in each layer of a deep convolutional neural network and report a few surprising results. Transferability is negatively affected by two distinct issues: (1) the specialization of higher layer neurons to their original task at the expense of performance on the target task, which was expected, and (2) optimization difficulties related to splitting networks between co-adapted neurons, which was not expected.

If you looking further to read more research paper here I have a few free sources that I too prefer:

Youtube source for AI papers :

If you prefer to watch then you can go for Two Minute Papers – a youtube channel that explains all these research paper using animation.

About the author

Vikram singh

Founder of Ai Venture,
An artificial intelligence specialist who teaches developers how to get results with modern AI methods via hands-on tutorials.
GANs are my favorite one.

View all posts