Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

We propose a new method to compare numbers which are encrypted by Homomorphic Encryption (HE). Previously, comparison and min/max functions were evaluated using Boolean functions where input numbers are encrypted bit-wise. However, the bit-wise encryption methods require relatively expensive computations for basic arithmetic operations such as addition and multiplication.

Numerical Method for Comparison on Homomorphically Encrypted Numbers

Image hashing with color vector angle

We present RONEC - the Named Entity Corpus for the Romanian language. The corpus contains over 26000 entities in ~5000 annotated sentences, belonging to 16 distinct classes. The sentences have been extracted from a copy-right free newspaper, covering several styles. This corpus represents the first initiative in the Romanian language space specifically targeted for named entity recognition. It is available in BRAT and CoNLL-U Plus formats, and it is free to use and extend at github.com/dumitrescustefan/ronec

Introducing RONEC - the Romanian Named Entity Corpus.

This paper presents a novel image hashing method for authentication and tampering detection. Creation, modification and transfer of multimedia data becomes an easy task due to digitization. Integrity is very important for crucial and sensitive matters like medical records, legal matters, scientific research, forensic investigations and government documents. Image hashing is one of the popular method to maintain integrity of image. We proposed AQ-CSLBP (Average Compressed Center Symmetric Local Binary Pattern) as a feature descriptor for image hashing. First, image is divided into sub blocks, AQ-CSLBP is applied on each sub block to generate 8 bin histogram as a feature. Then, we used double bit quantization to generate hash code for the image. The proposed method is compared with the existing methods by way of quantitative analysis, it has been proved that the proposed method works well in authentication scenario with less hash length and more discrimination power.

Image hashing using AQ-CSLBP with double bit quantization

Robust image hashing seeks to transform a given input image into a shorter hashed version using a key-dependent non-invertible transform. These hashes find extensive applications in content authentication, image indexing for database search and watermarking. Modern robust hashing algorithms consist of feature extraction, a randomization stage to introduce non-invertibility, followed by quantization and binary encoding to produce a binary hash. This paper describes a novel algorithm for generating an image hash based on Log-Polar transform features. The Log-Polar transform is a part of the Fourier-Mellin transformation, often used in image recognition and registration techniques due to its invariant properties to geometric operations. First, we show that the proposed perceptual hash is resistant to content-preserving operations like compression, noise addition, moderate geometric and filtering. Second, we illustrate the discriminative capability of our hash in order to rapidly distinguish between two perceptually different images. Third, we study the security of our method for image authentication purposes. Finally, we show that the proposed hashing method can provide both excellent security and robustness.

Efficient and robust perceptual hashing using log-polar image representation

The paper presents (1) a new library (API) that provides easy access to the Romanian WordNet and (2) an application based on the API to perform embedded vector retrofitting. The new API (further referred to as RoWn)is built in Python and offers direct access to all the data provided in the Romanian WordNet. It implements all basic I/O and query operations. As RoWnis based on a directed graph structure powered by the versatile networkx library, users are provided with the groundwork to implement powerful graph algorithms. The second part of the paper presents an application built on RoWn: the process of vector retrofitting. “Retrofitting” refers to the semantic specialization of word vectors, a process of fine-tuning each vector under a specified constraint. We use the synonymy/antonymy relations extracted from RoWnto tune the word vectors under these semantic constraints, effectively specializing the vector space.

RoWordNet – A Python API for the Romanian WordNet

/pdf/liro-benchmark-and-leaderboard-for-romanian-language-tasks-1nxz9hgtu3.pdf

LiRo: Benchmark and leaderboard for Romanian language tasks

Neural networks started to be developed around the idea of creating models of real neural systems because of the existing need in understanding how biological systems work. New areas of neural computing are trying to make at least one step beyond what digital computing means. The key point is based on learning rather than programming. We designed a mathematical model for information processing. The neuron model is viewed from inside as a feedback system that controls the information flow. The process of learning at ”molecular” level (internal neural learning), under the form of a computational algorithm inspired by a real brain functioning, has been introduced.

View from Inside One Neuron

The cloud computing providers need to offer security warranties. As we all know, one of the critical points is the confidentiality and access to customer data which, these days, is migrated and managed in cloud environments. In this sense, one solution is based on encrypting data before its upload in cloud. But this approach sets a limit regarding data processing. In this article we present a practical application of the homomorphic encryption schemes, namely the problem of finding maximum/minimum from a collection of encrypted integers. First, we present our algorithm that can be run directly in cloud without the need for an intermediate data exchange with the client. Second, our experimental results show the time resources necessary to evaluate the proposed algorithm.

https://www.acad.ro/sectii2002/proceedings/doc2015-3s/08-Togan.pdf

Luciana Morogan

Papers

Efficient and robust perceptual hashing using log-polar image representation

RoWordNet – A Python API for the Romanian WordNet

LiRo: Benchmark and leaderboard for Romanian language tasks

View from Inside One Neuron

Comparison-based applications for fully homomorphic encrypted data