Results 21 to 30 of about 295,552 (260)

Review of Multi-Criteria Decision-Making Methods in Finance Using Explainable Artificial Intelligence

Frontiers in Artificial Intelligence, 2022
The influence of Artificial Intelligence is growing, as is the need to make it as explainable as possible. Explainability is one of the main obstacles that AI faces today on the way to more practical implementation.
Jurgita Černevičienė, Audrius Kabašinskas   +1 more
doaj   +1 more source

Imparting Interpretability to Word Embeddings while Preserving Semantic Structure

, 2020
As an ubiquitous method in natural language processing, word embeddings are extensively employed to map semantic properties of words into a dense vector representation.
Koç, Aykut, Ozaktas, Haldun M., Senel, Lutfi Kerem, Utlu, Ihsan, Şahinuç, Furkan   +4 more
core   +2 more sources

Emulating quantum dynamics with neural networks via knowledge distillation

Frontiers in Materials, 2023
We introduce an efficient training framework for constructing machine learning-based emulators and demonstrate its capability by training an artificial neural network to predict the time evolution of quantum wave packets propagating through a potential ...
Yu Yao, Chao Cao, Stephan Haas, Mahak Agarwal, Divyam Khanna, Marcin Abram, Marcin Abram   +6 more
doaj   +1 more source

Axiomatic Interpretability for Multiclass Additive Models

, 2019
Generalized additive models (GAMs) are favored in many regression and binary classification problems because they are able to fit complex, nonlinear functions while still remaining interpretable.
Caruana, Rich, Chajewska, Urszula, Koch, Paul, Lou, Yin, Tan, Sarah, Zhang, Xuezhou   +5 more
core   +1 more source

Computational Analysis of Pathological Image Enables Interpretable Prediction for Microsatellite Instability

Frontiers in Oncology, 2022
BackgroundMicrosatellite instability (MSI) is associated with several tumor types and has become increasingly vital in guiding patient treatment decisions; however, reasonably distinguishing MSI from its counterpart is challenging in clinical practice ...
Jin Zhu, Wangwei Wu, Yuting Zhang, Shiyun Lin, Yukang Jiang, Ruixian Liu, Heping Zhang, Xueqin Wang   +7 more
doaj   +1 more source

Modeling Local Demand for Mobile Spectrum: An Interpretable Machine Learning Approach

IEEE Open Journal of the Communications Society
With the expansion of 5G networks and the ongoing development of future 6G networks, the demand for mobile spectrum is expected to continue to grow, particularly at a local level.
Janaki Parekh, Elizabeth Yackoboski, Amir Ghasemi, Halim Yanikomeroglu   +3 more
doaj   +1 more source

Semantic Structure and Interpretability of Word Embeddings

, 2018
Dense word embeddings, which encode semantic meanings of words to low dimensional vector spaces have become very popular in natural language processing (NLP) research due to their state-of-the-art performances in many NLP tasks.
Cukur, Tolga, Koc, Aykut, Senel, Lutfi Kerem, Utlu, Ihsan, Yucesoy, Veysel   +4 more
core   +1 more source

Interpretable Chinese Fake News Detection With Chain-of-Thought and In-Context Learning

IEEE Access
The spread of fake news through on-line platforms poses a significant threat to public trust and social stability, especially in resource-constrained Chinese domains.
Bingyi Liu, Anqi Wang, Chengqian Xia
doaj   +1 more source

Interpreters and interpreting: shifting the balance?

The Translator, 2022
The role of interpreters has been shaped by changing social contexts throughout the millennial history of this occupation, but demographic, educational, legal and technological developments have accelerated since the late 20th century and given rise to new forms of interpreting with the potential of reshaping the way interpreting is conceived.
openaire   +1 more source

Understanding Software Defect Prediction Through eXplainable Neural Additive Models

IEEE Access
Software defect prediction, leveraging machine learning techniques to proactively identify potential defects in software systems, plays a crucial role in enhancing software quality and reliability.
Ruiqi He, Yong Li, Chi Sun
doaj   +1 more source