| |
|
|
| |
| | Mariana Damova is the CEO of Mozaika, a company providing research and solutions for data science, natural interfaces, and human insight. Mozaika specializes in building semantic information infrastructures in different verticals, such as business information delivery, human resources management, cultural heritage, earth observation, and water management. Her background is in natural language processing, semantic web technologies, and artificial intelligence (AI), with significant academic and industry experience in Europe and North America. She has taught graduate courses, conducted research, and led international interdisciplinary projects and teams on virtual customer service, speech-to-speech machine translation, search based on linguistic principles, voice-enabled emotion recognition, an expert system supporting child protective services, water resources management, content mapping, and historical archives. She has collaborated with many different universities and organizations, including The National Archives of the UK, the British Museum, the Historical Archives of the European Commission, the European Space Agency, Europeana, and the Bulgarian Academy of Sciences. Mariana holds a PhD from the University of Stuttgart and a mini-MBA from McGill University, and currently teaches a graduate course at New Bulgarian University. She has been a reviewer for Computing Reviews since 2008, and has authored more than 50 publications (books and papers) related to linguistics and semantic technologies. Mariana enjoys museums, theater, and reading. |
| |
| |
|
Date Reviewed |
|
| |
1 - 10 of 60
reviews
|
|
|
 |
|
|
|
|
Gradient expectations: structure, origins, and synthesis of predictive neural networks
Downing K., MIT Press, Cambridge, MA, 2023. 224 pp. Type: Book (0262545616)
A very interesting and well-grounded work, Gradient expectations provides a thorough overview and explanation of the structure and origins of prediction and predictive neural networks....
|
Nov 6 2023 |
|
|
|
|
|
|
PyTorch recipes: a problem-solution approach to build, train and deploy neural network models (2nd ed.)
Mishra P., Apress, New York, NY, 2023. 290 pp. Type: Book (978-1484289242)
Full of lengthy code examples, PyTorch recipes is a very good textbook for beginner and intermediary neural network developers using PyTorch....
|
Jul 24 2023 |
|
|
|
|
|
|
 DARPA’s explainable artificial intelligence (XAI) program
Gunning D. IUI 2019 (Proceedings of the 24th International Conference on Intelligent User Interfaces, Marina del Ray, California, Mar 17-20, 2019) ii-ii, 2019. Type: Proceedings
This very interesting survey talk provides extensive, high-level insight into the midterm progress of this advanced research endeavor....
|
Jul 21 2021 |
|
|
|
|
|
|
Research on text location and recognition in natural images with deep learning
Zhang P., Shi Z., Gao H. ICAAI 2018 (Proceedings of the 2nd International Conference on Advances in Artificial Intelligence, Barcelona, Spain, Oct 6-8, 2018) 1-6, 2018. Type: Proceedings
A technical account, this paper reports on experiments carried out with combinations of deep learning techniques. The purpose of the proposed research is to explore and evaluate methods for text location and recognition in images....
|
Jan 14 2021 |
|
|
|
|
|
|
Indonesian automatic text summarization based on a new clustering method in sentence level
Cai Z., Lin N., Ma C., Jiang S. BDE 2019 (Proceedings of the 2019 International Conference on Big Data Engineering, Hong Kong, Hong Kong, Jun 11-13, 2019) 30-35, 2019. Type: Proceedings
A sentence-centered account of text summarization, this work can be applied to any language. Characteristics of the Indonesian language are irrelevant to the proposed approach and are not discussed. Neither is the suitability of the pr...
|
Oct 30 2020 |
|
|
|
|
|
|
DeepTest: automated testing of deep-neural-network-driven autonomous cars
Tian Y., Pei K., Jana S., Ray B. ICSE 2018 (Proceedings of the 40th International Conference on Software Engineering, Gothenburg, Sweden, May 27-Jun 3, 2018) 303-314, 2018. Type: Proceedings
A very promising and well-argued account, this paper presents a novel approach to systematically testing and automatically detecting erroneous behaviors in deep neural network (DNN)-driven vehicles....
|
Jun 23 2020 |
|
|
|
|
|
|
An improved algorithm for solving scheduling problems by combining generative adversarial network with evolutionary algorithms
Chen M., Yu R., Xu S., Luo Y., Yu Z. CSAE 2019 (Proceedings of the 3rd International Conference on Computer Science and Application Engineering, Sanya, China, Oct 22-24, 2019) 1-7, 2019. Type: Proceedings
This paper discusses the optimization of results derived from evolutionary algorithms by augmenting them with generative adversarial nets (GAN). The proposed research presents a hybrid algorithm that combines GAN with a genetic algorit...
|
Jun 4 2020 |
|
|
|
|
|
|
Neuromemrisitive architecture of HTM with on-device learning and neurogenesis
Zyarah A., Kudithipudi D. ACM Journal on Emerging Technologies in Computing Systems 15(3): 1-24, 2019. Type: Article
This very comprehensive technical account presents a thoroughly worked out “architecture for the spatial pooler (SP)” of the hierarchical temporal memory (HTM) algorithm. This algorithm is designed to produce invari...
|
Oct 11 2019 |
|
|
|
|
|
|
How testing helps to diagnose proof failures
Petiot G., Kosmatov N., Botella B., Giorgetti A., Julliand J. Formal Aspects of Computing 30(6): 629-657, 2018. Type: Article
Petiot et al. present testing software components that help optimize the effort of “applying deductive verification to formally prove that a [computer] program respects its formal specification.”...
|
May 10 2019 |
|
|
|
|
|
|
Neural network classifiers using a hardware-based approximate activation function with a hybrid stochastic multiplier
Li B., Qin Y., Yuan B., Lilja D. ACM Journal on Emerging Technologies in Computing Systems 15(1): 1-21, 2019. Type: Article
Li et al. present a novel approach for optimizing neural network implementations, that is, “a new architecture of stochastic neural networks” with a hidden approximate activation function and a hybrid stochastic mul...
|
May 1 2019 |
|
|
|
|
|
| |
|
|
| |
|
|
