2017
DOI: 10.3233/ds-170004
|View full text |Cite
|
Sign up to set email alerts
|

Data Science and symbolic AI: Synergies, challenges and opportunities

Abstract: Editor: Tobias Kuhn (https://orcid.org/0000-0002-1267-0234) Solicited reviews: anonymous reviewer; Rinke Hoekstra (https://orcid.org/0000-0001-7076-9083); Agnieszka Ławrynowicz (https://orcid.org/0000-0002-2442-345X); Honghan Wu (https://orcid.org/0000-0002-0213-5668) Received 21 February 2017 Accepted 27 April 2017Abstract. Symbolic approaches to Artificial Intelligence (AI) represent things within a domain of knowledge through physical symbols, combine symbols into symbol expressions, and manipulate symbols … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
18
0
1

Year Published

2018
2018
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 30 publications
(19 citation statements)
references
References 50 publications
0
18
0
1
Order By: Relevance
“…In the recent years, the historical dichotomy between the "two souls" of AI has been reconciled, in favor of a comprehensive vision where symbolic and sub-symbolic approaches are seen as complementary-rather than in a competition-so that they mutually soften their corners [155][156][157] (see Figure 1). While symbolic approaches are well suited for relatively small-sized problems implying complex but exact tasks-possibly relying on structured data-sub-symbolic approaches are best suited to use cases processing big (possibly huge) amounts of possibly unstructured data-where errors, or lack of precision, are tolerated to some extent, if unavoidable.…”
Section: Integration Of Symbolic and Sub-symbolic Aimentioning
confidence: 99%
“…In the recent years, the historical dichotomy between the "two souls" of AI has been reconciled, in favor of a comprehensive vision where symbolic and sub-symbolic approaches are seen as complementary-rather than in a competition-so that they mutually soften their corners [155][156][157] (see Figure 1). While symbolic approaches are well suited for relatively small-sized problems implying complex but exact tasks-possibly relying on structured data-sub-symbolic approaches are best suited to use cases processing big (possibly huge) amounts of possibly unstructured data-where errors, or lack of precision, are tolerated to some extent, if unavoidable.…”
Section: Integration Of Symbolic and Sub-symbolic Aimentioning
confidence: 99%
“…This subsection details the history and types of AI and its implications as discussed over the years. AI can be described as a cluster of technologies [15] and approaches, that is, statistical and symbolic [16] that aim at mimicking human cognitive functions [17] or exhibiting aspects of human intelligence by performing various tasks, mostly preceding analytical, analytical mostly preceding intuitive and intuitive mostly preceding empathetic intelligence [18].…”
Section: Artificial Intelligencementioning
confidence: 99%
“…Conserve and sustainably use the oceans, seas, and marine resources for sustainable development 15. Protect, restore, and promote the sustainable use of terrestrial ecosystems, sustainably manage forests, combat desertification, and halt and reverse land degradation and biodiversity loss 16. Promote peaceful and inclusive societies for sustainable development, provide access to justice for all, and build effective, accountable, and inclusive institutions at all levels 17.…”
mentioning
confidence: 99%
“…First, their implicit black-box nature can make them unsuitable to domains where verifiability is important [27]; moreover, their inability to reason at an abstract level makes it difficult to implement high-level cognitive functions, such as transfer learning, analogical reasoning, and hypothesis-based reasoning [15]. This is why several works in the last decade have focussed on extracting symbolic rules [28] from the knowledge implicit in a black-box model.…”
Section: Symbolic Vs Non-symbolic Techniques: Features and Synergiesmentioning
confidence: 99%
“…Symbolic approaches, on the other hand, represent things within a domain of knowledge through symbols, combine symbols into symbol expressions, and manipulate the latter, possibly through inferential processes. Symbolic representations feature two important properties that we intend to focus on, among the many [28]:…”
Section: Symbolic Vs Non-symbolic Techniques: Features and Synergiesmentioning
confidence: 99%