scholarly journals PCIV method for Indirect Bias Quantification in AI and ML Models

2021 ◽  
pp. 273-279
Author(s):  
Ashish Garg ◽  
Dr. Rajesh SL
Keyword(s):  
Neural Networks ◽  
Black Box ◽  
Training Data ◽  
Access To Services ◽  
Ethical Aspects ◽  
Ensemble Techniques ◽  
Methodical Approach ◽  
Wide Range ◽  
The World ◽  
Bias Detection

Data Scientists nowadays make extensive use of black-box AI models (such as Neural Networks and the various ensemble techniques) to solve various business problems. Though these models often provide higher accuracy, these models are also less explanatory at the same time and hence more prone to bias. Further, AI systems rely upon the available training data and hence remain prone to data bias as well. Many sensitive attributes such as race, religion, gender, ethnicity, etc. can form the basis of unethical bias in data or the algorithm. As the world is becoming more and more dependent on AI algorithms for making a wide range of decisions such as to determine access to services such as credit, insurance, and employment, the fairness & ethical aspects of the models are becoming increasingly important. There are many bias detection & mitigation algorithms which have evolved and many of the algorithms handle indirect attributes as well without requiring to explicitly identify them. However, these algorithms have gaps and do not quantify the indirect bias. This paper discusses the various bias detection methodologies and various tools/ libraries to detect & mitigate bias. Thereafter, this paper presents a new methodical approach to detect and quantify indirect bias in an AI/ ML models.

Knowledge Discovery with Artificial Neural Networks

2011 ◽  
pp. 669-673
Author(s):  
Juan R. Rabuñal Dopico ◽  
Daniel Rivero Cebrian ◽  
Julián Dorado de la Calle ◽  
Nieves Pedreira Souto
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Knowledge Discovery ◽  
Powerful Technique ◽  
Complex Problems ◽  
New Information ◽  
Wide Range ◽  
The World ◽  
Artificial Neural

The world of Data Mining (Cios, Pedrycz & Swiniarrski, 1998) is in constant expansion. New information is obtained from databases thanks to a wide range of techniques, which are all applicable to a determined set of domains and count with a series of advantages and inconveniences. The Artificial Neural Networks (ANNs) technique (Haykin, 1999; McCulloch & Pitts, 1943; Orchad, 1993) allows us to resolve complex problems in many disciplines (classification, clustering, regression, etc.), and presents a series of advantages that convert it into a very powerful technique that is easily adapted to any environment. The main inconvenience of ANNs, however, is that they can not explain what they learn and what reasoning was followed to obtain the outputs. This implies that they can not be used in many environments in which this reasoning is essential.

scholarly journals Convolutional Neural Networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Teja Kattenborn ◽  
Jana Eichel ◽  
Fabian Ewald Fassnacht
Keyword(s):  
Neural Networks ◽  
High Resolution ◽  
Convolutional Neural Networks ◽  
Low Cost ◽  
Training Data ◽  
Observation Data ◽  
Visual Interpretation ◽  
Fine Grained ◽  
Wide Range ◽  
Vegetation Species

AbstractRecent technological advances in remote sensing sensors and platforms, such as high-resolution satellite imagers or unmanned aerial vehicles (UAV), facilitate the availability of fine-grained earth observation data. Such data reveal vegetation canopies in high spatial detail. Efficient methods are needed to fully harness this unpreceded source of information for vegetation mapping. Deep learning algorithms such as Convolutional Neural Networks (CNN) are currently paving new avenues in the field of image analysis and computer vision. Using multiple datasets, we test a CNN-based segmentation approach (U-net) in combination with training data directly derived from visual interpretation of UAV-based high-resolution RGB imagery for fine-grained mapping of vegetation species and communities. We demonstrate that this approach indeed accurately segments and maps vegetation species and communities (at least 84% accuracy). The fact that we only used RGB imagery suggests that plant identification at very high spatial resolutions is facilitated through spatial patterns rather than spectral information. Accordingly, the presented approach is compatible with low-cost UAV systems that are easy to operate and thus applicable to a wide range of users.

scholarly journals Distinguishing between recent balancing selection and incomplete sweep using deep neural networks

2020 ◽  
Author(s):  
Ulas Isildak ◽  
Alessandro Stella ◽  
Matteo Fumagalli
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Balancing Selection ◽  
False Positive Rate ◽  
Genomic Data ◽  
Training Data ◽  
Functional Changes ◽  
Wide Range ◽  
Recent Selection

1AbstractBalancing selection is an important adaptive mechanism underpinning a wide range of phenotypes. Despite its relevance, the detection of recent balancing selection from genomic data is challenging as its signatures are qualitatively similar to those left by ongoing positive selection. In this study we developed and implemented two deep neural networks and tested their performance to predict loci under recent selection, either due to balancing selection or incomplete sweep, from population genomic data. Specifically, we generated forward-intime simulations to train and test an artificial neural network (ANN) and a convolutional neural network (CNN). ANN received as input multiple summary statistics calculated on the locus of interest, while CNN was applied directly on the matrix of haplotypes. We found that both architectures have high accuracy to identify loci under recent selection. CNN generally outperformed ANN to distinguish between signals of balancing selection and incomplete sweep and was less affected by incorrect training data. We deployed both trained networks on neutral genomic regions in European populations and demonstrated a lower false positive rate for CNN than ANN. We finally deployed CNN within the MEFV gene region and identified several common variants predicted to be under incomplete sweep in a European population. Notably, two of these variants are functional changes and could modulate susceptibility to Familial Mediterranean Fever, possibly as a consequence of past adaptation to pathogens. In conclusion, deep neural networks were able to characterise signals of selection on intermediate-frequency variants, an analysis currently inaccessible by commonly used strategies.

Sanitizing hidden activations for improving adversarial robustness of convolutional neural networks

2021 ◽  
pp. 1-11
Author(s):  
Tianshi Mu ◽  
Kequan Lin ◽  
Huabing Zhang ◽  
Jian Wang
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Black Box ◽  
Experimental Results ◽  
Amplification Effect ◽  
Wide Range ◽  
Adversarial Examples

Deep learning is gaining significant traction in a wide range of areas. Whereas, recent studies have demonstrated that deep learning exhibits the fatal weakness on adversarial examples. Due to the black-box nature and un-transparency problem of deep learning, it is difficult to explain the reason for the existence of adversarial examples and also hard to defend against them. This study focuses on improving the adversarial robustness of convolutional neural networks. We first explore how adversarial examples behave inside the network through visualization. We find that adversarial examples produce perturbations in hidden activations, which forms an amplification effect to fool the network. Motivated by this observation, we propose an approach, termed as sanitizing hidden activations, to help the network correctly recognize adversarial examples by eliminating or reducing the perturbations in hidden activations. To demonstrate the effectiveness of our approach, we conduct experiments on three widely used datasets: MNIST, CIFAR-10 and ImageNet, and also compare with state-of-the-art defense techniques. The experimental results show that our sanitizing approach is more generalized to defend against different kinds of attacks and can effectively improve the adversarial robustness of convolutional neural networks.

scholarly journals Brightness Invariant Deep Spectral Super-Resolution

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5789
Author(s):  
Tarek Stiebel ◽  
Dorit Merhof
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Scale Invariance ◽  
Super Resolution ◽  
Training Data ◽  
Essential Property ◽  
Practical Applications ◽  
Wide Range ◽  
Cheap Alternative ◽  
The Moment

Spectral reconstruction from RGB or spectral super-resolution (SSR) offers a cheap alternative to otherwise costly and more complex spectral imaging devices. In recent years, deep learning based methods consistently achieved the best reconstruction quality in terms of spectral error metrics. However, there are important properties that are not maintained by deep neural networks. This work is primarily dedicated to scale invariance, also known as brightness invariance or exposure invariance. When RGB signals only differ in their absolute scale, they should lead to identical spectral reconstructions apart from the scaling factor. Scale invariance is an essential property that signal processing must guarantee for a wide range of practical applications. At the moment, scale invariance can only be achieved by relying on a diverse database during network training that covers all possibly occurring signal intensities. In contrast, we propose and evaluate a fundamental approach for deep learning based SSR that holds the property of scale invariance by design and is independent of the training data. The approach is independent of concrete network architectures and instead focuses on reevaluating what neural networks should actually predict. The key insight is that signal magnitudes are irrelevant for acquiring spectral reconstructions from camera signals and are only useful for a potential signal denoising.

scholarly journals Prediction of blast loading in an internal environment using artificial neural networks

2020 ◽  
pp. 204141962097057
Author(s):  
Adam A Dennis ◽  
Jordan J Pannell ◽  
Danny J Smyl ◽  
Sam E Rigby
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Structure ◽  
Computational Cost ◽  
Blast Loading ◽  
Training Data ◽  
Training Dataset ◽  
Internal Environment ◽  
Wide Range ◽  
Artificial Neural

Explosive loading in a confined internal environment is highly complex and is driven by nonlinear physical processes associated with reflection and coalescence of multiple shock fronts. Prediction of this loading is not currently feasible using simple tools, and instead specialist computational software or practical testing is required, which are impractical for situations with a wide range of input variables. There is a need to develop a tool which balances the accuracy of experiments or physics-based numerical schemes with the simplicity and low computational cost of an engineering-level predictive approach. Artificial neural networks (ANNs) are formed of a collection of neurons that process information via a series of connections. When fully trained, ANNs are capable of replicating and generalising multi-parameter, high-complexity problems and are able to generate new predictions for unseen problems (within the bounds of the training variables). This article presents the development and rigorous testing of an ANN to predict blast loading in a confined internal environment. The ANN was trained using validated numerical modelling data, and key parameters relating to formulation of the training data and network structure were critically analysed in order to maximise the predictive capability of the network. The developed network was generally able to predict specific impulses to within 10% of the numerical data: 90% of specific impulses in the unseen testing data, and between 81% and 87% of specific impulses for data from four additional unseen test models, were predicted to this accuracy. The network was highly capable of generalising in areas adjacent to reflecting surfaces and as those close to ambient outflow boundaries. It is shown that ANNs are highly suited to modelling blast loading in a confined internal environment, with significant improvements in accuracy achievable if a robust, well distributed training dataset is used with a network structure that is tailored to the problem being solved.

scholarly journals The Contribution of American Nurses to the Evolution of the International Council of Nurses

2020 ◽  
Vol 25 (2) ◽  
Author(s):  
Stephanie Ferguson ◽  
David Benton
Keyword(s):  
Services Quality ◽  
The United States ◽  
Nursing Profession ◽  
Collaborative Effort ◽  
Access To Services ◽  
International Council ◽  
The Past ◽  
Wide Range ◽  
The World

As the nursing profession celebrates the International Year of the Nurse and Midwife, it is time to take stock of the contribution that American nurses and the United States have made to the evolution of the International Council of Nurses (ICN). American nurses were involved even before the conception of the organization and have played a significant role in its leadership and development. Nurses who have been active in the American Nurses Association (ANA) have often been heavily involved in various aspects of ICN governance and evolution. Additionally, several American philanthropic foundations and corporate donors have supported a wide range of ICN activity that has helped advance the nursing profession around the world. As we celebrate Nightingale’s legacy, we should also think about all the nurses who have brought us to this point from the past, and those collaborating today and tomorrow. Examining the contribution of American nursing highlights the fact that this collaborative effort of the world’s nurses is needed if we are to optimize access to services, quality of care and sustainability of the nursing profession.

International Telesupervision: The Clinical Fellowship Experience

2017 ◽  
Vol 2 (11) ◽  
pp. 73-78
Author(s):  
David W. Rule ◽  
Lisa N. Kelchner
Keyword(s):  
Graduate Students ◽  
Clinical Supervision ◽  
Rural Areas ◽  
The United States ◽  
Speech Language Pathology ◽  
Access To Services ◽  
East African ◽  
The World ◽  
Language Pathology ◽  
National Certification

Telepractice technology allows greater access to speech-language pathology services around the world. These technologies extend beyond evaluation and treatment and are shown to be used effectively in clinical supervision including graduate students and clinical fellows. In fact, a clinical fellow from the United States completed the entire supervised clinical fellowship (CF) year internationally at a rural East African hospital, meeting all requirements for state and national certification by employing telesupervision technology. Thus, telesupervision has the potential to be successfully implemented to address a range of needs including supervisory shortages, health disparities worldwide, and access to services in rural areas where speech-language pathology services are not readily available. The telesupervision experience, potential advantages, implications, and possible limitations are discussed. A brief guide for clinical fellows pursuing telesupervision is also provided.

Creative Strategy Used in Electronic Advertising

GIS Business ◽  
2019 ◽  
Vol 14 (6) ◽  
pp. 597-606
Author(s):  
Dr. Maha Mustafa Omer Abdalaziz
Keyword(s):  
The Internet ◽  
Business Organizations ◽  
Creative Strategy ◽  
Electronic Environment ◽  
Wide Range ◽  
The World ◽  
Technological Developments ◽  
Electronic Advertising

The study aims at the technological developments that are taking place in the world and have impacted on all sectors and fields and imposed on the business organizations and commercial companies to carry out their marketing and promotional activities within the electronic environment. The most prominent of these developments is the emergence of the concept of electronic advertising which opened a wide range of companies and businessmen to advertise And to promote their products and their work easily through the Internet, which has become full of electronic advertising, and in light of that will discuss the creative strategy used in electronic advertising;

Aplikasi Kuartu Berbasis Android Sebagai Media Pertukaran Informasi Kartu Nama

2017 ◽  
Vol 9 (1) ◽  
pp. 25-32
Author(s):  
Nandi Syukri ◽  
Eko Budi Setiawan
Keyword(s):  
Mobile Devices ◽  
Information Exchange ◽  
Smart Phone ◽  
Black Box ◽  
Qr Code ◽  
Business Card ◽  
Large Numbers ◽  
The World ◽  
The Face ◽  
Index Terms

Business Card is the most efficient, effective and appropriate tool for every business men no matter they are owners, employees, more over marketers to provide information about their businesses. Unfortunately, it is very difficult to bring and manage business card in large numbers also to remember the face of the business card owner. A Business Card application need to be built to solve all those issues mentioned above. The Application or software must be run in media which can be accessed anywhere and anytime such as smart phone. Kuartu is as business card application run in mobile devices. Kuartu is developed using object base modeling for mobile sub system. The platform of the mobile sub system is android, as it is the most widely used platform in the world. The Kuartu application utilizing NFC and QR Code technology to support the business card information exchange and the Chatting feature for communication. Based on the experiment and test using black box methodology, it can be concluded that Kuartu application makes business card owner to communicate each other easily, business card always carried, easy to manage the cards and information of the business card owner can be easily obtained. Index Terms— Business Card, Android, Kuartu, NFC, QrCode, Chatting.

Sign in / Sign up

Export Citation Format

Share Document