arXiv subjects

Alex Zhavoronkov

Publications and source records attributed to Alex Zhavoronkov.

21 records · Page 2Linked to original sources

arXiv2017

Evaluating race and sex diversity in the world's largest companies using deep neural networks

Diversity is one of the fundamental properties for the survival of species, populations, and organizations. Recent advances in deep learning allow for the rapid and automatic assessment of organizational diversity and possible discrimination by race, sex, age and other parameters. Automating the process of assessing the organizational diversity using the deep neural networks and eliminating the human factor may provide a set of real-time unbiased reports to all stakeholders. In this pilot study we applied the deep-learned predictors of race and sex to the executive management and board member profiles of the 500 largest companies from the 2016 Forbes Global 2000 list and compared the predicted ratios to the ratios within each company's country of origin and ranked them by the sex-, age- and race- diversity index (DI). While the study has many limitations and no claims are being made concerning the individual companies, it demonstrates a method for the rapid and impartial assessment of organizational diversity using deep neural networks.

cs.CY↗

arXiv2015

GrantMed: a new, international system for tracking grants and funding trends in the life sciences

Despite the success of PubMed and other search engines in managing the massive volume of biomedical literature and the retrieval of individual publications, grant-related data remains scattered and relatively inaccessible. This is problematic, as project and funding data has significant analytical value and could be integral to publication retrieval. Here, we introduce GrantMed, a searchable international database of biomedical grants that integrates some 20 million publications with the nearly 1.4 million research projects and 650 billion dollars of funding that made them possible. For any given topic in the life sciences, Grantmed provides instantaneous visualization of the past 30 years of dollars spent and projects awarded, along with detailed individual project descriptions, funding amounts, and links to investigators, research organizations, and resulting publications. It summarizes trends in funding and publication rates for areas of interest and merges data from various national grant databases to create one international grant tracking system. This information will benefit the research community and funding entities alike. Users can view trends over time or current projects underway and use this information to navigate the decision-making process in moving forward. They can view projects prior to publication and records of previous projects. Convenient access to this data for analytical purposes will be beneficial in many ways, helping to prevent project overlap, reduce funding redundancy, identify areas of success, accelerate dissemination of ideas, and expose knowledge gaps in moving forward. It is our hope that this will be a central resource for international life sciences research communities and the funding organizations that support them, ultimately streamlining progress.

cs.DL↗

arXiv2015

Models of Innate Neural Attractors and Their Applications for Neural Information Processing

In this work we reveal and explore a new class of attractor neural networks, based on inborn connections provided by model molecular markers, the molecular marker based attractor neural networks (MMBANN). We have explored conditions for the existence of attractor states, critical relations between their parameters and the spectrum of single neuron models, which can implement the MMBANN. Besides, we describe functional models (perceptron and SOM) which obtain significant advantages, while using MMBANN. In particular, the perceptron based on MMBANN, gets specificity gain in orders of error probabilities values, MMBANN SOM obtains real neurophysiological meaning, the number of possible grandma cells increases 1000- fold with MMBANN. Each set of markers has a metric, which is used to make connections between neurons containing the markers. The resulting neural networks have sets of attractor states, which can serve as finite grids for representation of variables in computations. These grids may show dimensions of d = 0, 1, 2,... We work with static and dynamic attractor neural networks of dimensions d = 0 and d = 1. We also argue that the number of dimensions which can be represented by attractors of activities of neural networks with the number of elements N=104 does not exceed 8.

q-bio.NC↗