An overview on data representation learning: From traditional feature learning to recent deep learning

Zhong, Guoqiang; Wang, Lina; Ling, Xiao; Dong, Junyu

doi:10.1016/j.jfds.2017.05.001

Cited by 152 publications

(95 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Caffe 7 is a C++ library that provides interfaces for Python and MATLAB [44]. It is a clean and modifiable framework, due to the fact that the model's representation is separate from the model's implementation [45].…”

Section: Deploying Deep Learning Methodsmentioning

confidence: 99%

Deep Learning Application in Security and Privacy – Theory and Practice: A Position Paper

Meister

Akram

Markantonakis

2019

Information Security Theory and Practice

View full text Add to dashboard Cite

Technology is shaping our lives in a multitude of ways. This is fuelled by a technology infrastructure, both legacy and state of the art, composed of a heterogeneous group of hardware, software, services and organisations. Such infrastructure faces a diverse range of challenges to its operations that include security, privacy, resilience, and quality of services. Among these, cybersecurity and privacy are taking the centre-stage, especially since the General Data Protection Regulation (GDPR) came into effect. Traditional security and privacy techniques are overstretched and adversarial actors have evolved to design exploitation techniques that circumvent protection. With the ever-increasing complexity of technology infrastructure, security and privacy-preservation specialists have started to look for adaptable and flexible protection methods that can evolve (potentially autonomously) as the adversarial actor changes its techniques. For this, Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) were put forward as saviours. In this paper, we look at the promises of AI, ML, and DL stated in academic and industrial literature and evaluate how realistic they are. We also put forward potential challenges a DL based security and privacy protection technique has to overcome. Finally, we conclude the paper with a discussion on what steps the DL and the security and privacy-preservation community have to take to ensure that DL is not just going to be hype, but an opportunity to build a secure, reliable, and trusted technology infrastructure on which we can rely on for so much in our lives.

show abstract

Section: Deploying Deep Learning Methodsmentioning

confidence: 99%

Deep Learning Application in Security and Privacy – Theory and Practice: A Position Paper

Meister

Akram

Markantonakis

2019

Information Security Theory and Practice

View full text Add to dashboard Cite

show abstract

“…One work with a promising title for researchers interested in using categorical data as input to neural networks is, "An overview on data representation learning: From traditional feature learning to recent deep learning" [14], by Zhong et al However, this work traces the history of data representation starting with principal component analysis ( PCA ) and linear discriminant analysis ( LDA ) (On a side note, the reader should be aware that the abbreviation LDA is often used for two different techniques in machine learning literature, Latent Dirichlet Allocation, or linear discriminant analysis). Zhong et al make a great contribution in describing PCA, LDA, and its descendants, but this work is not strictly dedicated to techniques for using categorical data in neural networks in the manner that this survey is.…”

Section: Related Workmentioning

confidence: 99%

Survey on categorical data for neural networks

2020

View full text Add to dashboard Cite

This survey investigates current techniques for representing qualitative data for use as input to neural networks. Techniques for using qualitative data in neural networks are well known. However, researchers continue to discover new variations or entirely new methods for working with categorical data in neural networks. Our primary contribution is to cover these representation techniques in a single work. Practitioners working with big data often have a need to encode categorical values in their datasets in order to leverage machine learning algorithms. Moreover, the size of data sets we consider as big data may cause one to reject some encoding techniques as impractical, due to their running time complexity. Neural networks take vectors of real numbers as inputs. One must use a technique to map qualitative values to numerical values before using them as input to a neural network. These techniques are known as embeddings, encodings, representations, or distributed representations. Another contribution this work makes is to provide references for the source code of various techniques, where we are able to verify the authenticity of the source code. We cover recent research in several domains where researchers use categorical data in neural networks. Some of these domains are natural language processing, fraud detection, and clinical document automation. This study provides a starting point for research in determining which techniques for preparing qualitative data for use with neural networks are best. It is our intention that the reader should use these implementations as a starting point to design experiments to evaluate various techniques for working with qualitative data in neural networks. The third contribution we make in this work is a new perspective on techniques for using categorical data in neural networks. We organize techniques for using categorical data in neural networks into three categories. We find three distinct patterns in techniques that identify a technique as determined, algorithmic, or automated. The fourth contribution we make is to identify several opportunities for future research. The form of the data that one uses as an input to a neural network is crucial for using neural networks effectively. This work is a tool for researchers to find the most effective technique for working with categorical data in neural networks, in big data settings. To the best of our knowledge this is the first in-depth look at techniques for working with categorical data in neural networks.

show abstract

“…1. Next, it is important to design a distinguisher that makes the quality of the spec by distinguishing between the real defect and the non-defect [5], [6].…”

Section: Detecting Defect Proceduresmentioning

confidence: 99%

76‐5: Late‐News Paper: Enhanced Productivity Performance through Detecting Defects on Surface of AMOLED Display

Park

Cho

Heo

et al. 2019

Symp Digest of Tech Papers

View full text Add to dashboard Cite

At this time, the system with advanced automatic detection capability has consistent execution results and has been verified that it can be used as a necessary tool for cost reduction and the quality control of the product, which is the value of the customer. It will contribute to reducing human error and minimizing defects by designing a system that relies on more mechanization automation, taking into account the characteristics of the machine as well as the role of humans and machines.

show abstract

An overview on data representation learning: From traditional feature learning to recent deep learning

Cited by 152 publications

References 74 publications

Deep Learning Application in Security and Privacy – Theory and Practice: A Position Paper

Deep Learning Application in Security and Privacy – Theory and Practice: A Position Paper

Survey on categorical data for neural networks

76‐5: Late‐News Paper: Enhanced Productivity Performance through Detecting Defects on Surface of AMOLED Display

Contact Info

Product

Resources

About