Abstract
SummaryMachine learning has been heavily researched and widely used in many disciplines. However, achieving high accuracy requires a large amount of data that is sometimes difficult, expensive, or impractical to obtain. Integrating human knowledge into machine learning can significantly reduce data requirement, increase reliability and robustness of machine learning, and build explainable machine learning systems. This allows leveraging the vast amount of human knowledge and capability of machine learning to achieve functions and performance not available before and will facilitate the interaction between human beings and machine learning systems, making machine learning decisions understandable to humans. This paper gives an overview of the knowledge and its representations that can be integrated into machine learning and the methodology. We cover the fundamentals, current status, and recent progress of the methods, with a focus on popular and new topics. The perspectives on future directions are also discussed.
Highlights
Machine learning has been heavily researched and widely used in many areas from object detection (Zou et al, 2019) and speech recognition (Graves et al, 2013) to protein structure prediction (Senior et al, 2020) and engineering design optimization (Deng et al, 2020; Gao and Lu, 2020; Wu et al, 2018)
KNOWLEDGE AND ITS REPRESENTATIONS Knowledge is categorized into general knowledge and domain knowledge as we mentioned earlier
Formed Knowledge Qualitative knowledge can be pre-processed in ways that it is expressed in more numerical formats for use in machine learning
Summary
Machine learning has been heavily researched and widely used in many areas from object detection (Zou et al, 2019) and speech recognition (Graves et al, 2013) to protein structure prediction (Senior et al, 2020) and engineering design optimization (Deng et al, 2020; Gao and Lu, 2020; Wu et al, 2018). Formed Knowledge Qualitative knowledge can be pre-processed in ways that it is expressed in more numerical formats for use in machine learning. One example is that empirical human knowledge in social science can be inserted into machine learning through qualitative coding (Chen et al, 2018) This technique assigns inferential labels to chunks of data, enabling later model development. Only few differential equations have explicit solutions, as long as their formats can be determined by domain knowledge, machine learning can numerically solve them This strategy inspires data-driven PDE/ODE solvers (Samaniego et al, 2020). Machine learning models, such as neural networks, can be built upon knowledge graph, as is further discussed in Section Design of Neuron Connections
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.