... .computerized neural networks,..., consist of neuron-like units. A homogeneous group of units makes up a layer They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis.
To achieve our goals we use descriptive metadata, i.e. keywords assigned by authors of papers published in this field and the Medical Subject Headings (MeSH) indexing terms assigned by MEDLINE indexers. We used MEDLINE to retrieve papers, as it consistently specifies MeSH headings. Our method followed these steps:
All search results are based on the numbers extracted from a snapshot of a search performed in October 2018. In order to retrieve papers including knowledge representation and the respective fields in AI, we used a simple search construct: pairs of authors’ keyword ‘ knowledge representation’ and the labels of MeSH index terms pertaining to AI, as shown in Figure 1 . In the same way, we retrieved the MeSH index term pairs, using the same simple search construct e.g., “Biological Ontologies”[All] AND “Natural Language Processing”[All]. As keywords are limited, and may not address all relevant aspects of indexed papers, we exploited text mining to gain insight into the frequencies of phrases that relate to the content descriptive metadata labels. Text mining on the abstracts of the papers followed a Wittgensteinian approach: interpreting the “meaning by usage” - the usage of the content metadata notions as words, referring to AI. 9 . We analyzed occurrences (phrase frequencies and collocation) of content descriptive metadata element labels as words used in the text of papers. We think that this work would provide a deeper understanding of the underlying conceptual structure of the field in research. To this end, a corpus was created consisting of the title, keywords, and abstract of the first 1,000 articles according to PubMed “Best Match” order.
Figure 2 shows the growth of various MeSH-defined AI fields as proportions of MEDLINE-indexed publications. The data regarding “ knowledge representation ” in MEDLINE were collected with the same search query formalism as the queries for those AI fields for which MeSH terms exist. In the last thirty years, research intensified significantly and the growth started in the eighties. The ratio of AI-related research output to all MEDLINE-indexed publications is presently about six times as much as it was at the beginning of the eighties. Some areas like (artificial) neural networks started to grow almost exponentially in the nineties - seemingly levelling out over time, after the year 2000. Other areas like machine learning show very steep growth in the last decade. There is a steady growth in the area of expert systems . The area of knowledge bases (KB) research started to grow with more research on biological ontologies understood by MeSH as a subcategory of KBs. More details and an actualized version with latest data are here: https://goo.gl/j4fvi4
Proportion of MEDLINE-indexed literature on nine areas of AI over time. The envelope curve is not data based but illustrates the cascading growth, the escalation of research.
The changes (and more specifically their relations to knowledge representation ) are further analyzed in this paper by text mining the relevant literature. The results are presented below in two steps.
Step 1: Investigation of the overall interaction among KR and various fields of AI in biomedical literature
Table 2 shows the extracted data. As described in the Methods section, the first level of the MeSH hierarchy classification is used together with ‘ biological ontologies’ - even though ‘ biological ontologies’ falls under the MeSH hierarchy ‘ knowledge bases’ . This is further addressed in the discussion section.
The red and the blue numbers show the two areas ( NeurNet and MachL ) mostly cross-cited with all others. Sums of cross-citations and standard deviations (SD) are calculated from the vertical and horizontal numbers (nine data elements - see as examples the red and blue numbers) for each area. In the case of ‘ heuristics ’, most of the data elements are zero, that is why calculating a standard deviation is not relevant. The standard deviation of these number series indicates how evenly a certain field is connected to others. Obviously, a higher SD means less uniform distribution.
For further visual analysis, overlapping citations among various AI areas are shown as a network diagram in Figure 3 . Nodes represent AI areas by their MeSH designations. Edges represent the overlaps, the cross citations among the nodes. In the depicted network, the nodes are proportionally sized to the number of cited literature areas. The width and the style of the edges correspond to the overlap among them. Widths of edges grow with the magnitude of the overlap. This network visualization helps to see the interconnectedness between the areas and the role of Knowledge Representation in this interdisciplinary arena.
AI fields citations in MEDLINE, viewed as a network, where nodes are the AI fields and edges are the cross-citations.
Step 2: Phrase frequency and collocation analysis of extracted abstracts
The above studied citation data cover over eighty thousand citations. A further, in-depth look a limited corpus containing the abstracts of the most relevant first thousand papers was established. This corpus had 246,308 total words, of which 21,842 are unique word forms. A simple phrase frequency analysis 8 shows that the following five AI fields occur among the most frequent terms in the corpus:
These frequencies show the most researched areas of AI, however they do not shed light to their interaction with the specific aspect of language and meaning, classically discussed as `knowledge representation’. The collocation of AI fields was measured in the same corpus as the phrase frequency , both the left and right window spans were set to the maximum of 20 terms distance. In an earlier paper 10 , authors realized that “... the central role of the term “concept” has been gradually abandoned ….”. The notion of ‘ concept ’ was a term central to what was called the field of research in ‘ knowledge representation’ . Therefore, in order to analyze the current corpus on AI, in addition to the notion of ‘knowledge representation’, the notions ‘language’ & ‘meaning’ were also brought to the collocation study. For the four most studied areas, collocation data found in the corpus are shown in Table 4 .
KR notions/AI Areas | Knowledge representation | Language | Meaning | Total |
---|---|---|---|---|
Robotics Fuzzy logic Neural networks Machine learning | 6 79 24 15 | 3 9 7 9 | 0 5 2 0 | 9 93 33 24 |
Principal findings.
Figure 1 shows that over time the various fields related to medical AI follow a cascading and explicitly escalating evolution. ‘ Expert systems’ studied in the eighties were followed by ‘ computer neural networks’ being in the lead in the nineties and the beginning of the twenty first century. This was followed by even more research focusing on ‘ robotics’ and currently on ‘ machine learning’ . At the same time, research goes on steadily in the other depicted fields. The cascade character might show us how new fields, or new names for old fields, take on and might also incorporate the results of previous areas. However, it is not trivial to see if ‘ machine learning’ will also take on the “cube root” function characteristics of other research fields, levelling out over time. Table 2 and Figure 3 show that although the research in medical AI has branched to a broad spectrum of fields, they are well interconnected. At the same time the interconnectedness varies greatly. ‘ Computer heuristics’ and ‘ biological ontologies’ are somewhat less interconnected to other fields, ‘ machine learning’ and ‘ computer-based neural networks’ are the most interconnected fields with all others. The term “ knowledge representation ” in the MeSH thesaurus itself is not part of an AI field, but is used in three entry terms for AI: Knowledge Representation (Computer) Knowledge Representations (Computer), Representation, Knowledge (Computer). Table 3 shows that the four areas ‘ robotic’ `, ‘ fuzzy logic’ , ‘ neural networks ’, and ‘ machine learning ’ seem to be by far the most mentioned researched areas, while ‘ expert systems ’, although above the limit of 50 citations, scores well below. Table 4 tells us that ‘ fuzzy logic’ seems to be the most collocated notion to the world of ‘ knowledge representation’ , ‘ meaning’, and ‘ language’ . This shows some advantage of the fuzzy approach to represent and to interpret medical knowledge. ‘ Neural networks’ and ‘ machine learning’ are also used in the conceptual neighborhood of knowledge representation. At the same time ‘robotics’ , while an important area in AI, seems to be somewhat isolated from the KR world. These results from text mining show that the various AI fields are well interconnected. It is interesting to see that the lowest standard deviation (SD) of cross citations to different areas occurs for our historically central concept ‘ knowledge representation ’. The relatively lowest SD shows that KR is the most “evenly” referred ‘notion’ till today. This finding provides a quantitative indicator suggesting that studying KR was (and is) at the origin of the wide spreading and branching fields of AI research. We will briefly highlight three interactions.
AI fields | Phrase examples | Count |
---|---|---|
Robotics | the robot robotic surgery of robotic a robot | 118 84 79 53 |
Fuzzy logic | neuro fuzzy fuzzy neural fuzzy inference fuzzy logic | 83 81 60 80 |
Neural networks | neural networks | 284 |
Machine learning | machine learning | 267 |
Expert systems | expert system | 62 |
Knowledge representation plays a role in robotics, for example for categorizing emotions 11 , learning cognitive robots to count 12 , representing and formalizing knowledge about care 13 . These examples show how knowledge representation can be an integral part of improving the functioning of robots. It apparently is yet too early to exploit the cognitive capacities of robots to contribute to knowledge representation, as no literature was found on this topic.
Interaction between knowledge representation and machine learning is yet limited, but needed. An early acknowledgement of this need, specifically for diagnostic image interpretation, is found in 14 . Already in 1988, it was stated that “Diagnostic image interpretation with learning capability demands a full model of the human expert’s competence, including a considerable variety of knowledge representation schemes and inference strategies, coordinated by a meta-process controller.” A recent approach is to combine graph data (represented in Resource Description Framework and Ontology Web Language) with neural networks to generate embeddings of nodes 15 . This combination results in embeddings that contain both explicit and implicit information. Machine learning can contribute to knowledge representation, e.g., by abstract feature selection, which has been applied for automated phenotyping in 16 . Finally, we notice that natural language processing is among the domains to which machine learning and knowledge representation are applied. For example, MedTAS/P combines these three areas, as described in 17 .
Not surprisingly, most of these overlapping studies focus on the fuzzy nature of our limited knowledge in explaining and understanding particular diseases (e.g. Economou et al. 18 ) in cardiology or in the field of oncology (see D’Aquin et al. 2004 19 ). However, interesting studies compare the “fuzzy” thinking with different approaches, where the “fuzziness” seems to be a connecting notion between the worlds of algorithmic and other approaches interpreting medical data, e.g. Douali et al., in 2014 20 , on fuzzy cognitive maps and Bayesian networks, and Kwiatkowska et al., in 2007 21 , on creating prediction rules using typicality measures. Another typical area for overlapping studies is the high level interpretation of medical knowledge, e.g., Bellamy, in 1997 22 , on “Medical diagnosis, diagnostic spaces, and fuzzy systems” and the work of Boegl et al., in 2004 23 , on knowledge acquisition in a fuzzy knowledge representation framework. Summing up this interaction of these two fields is quite broad and covers many different areas of medical information science.
Various widely divergent approaches involving, among others, fuzzy set theory 24 , Bayesian networks 25 , and artificial neural networks 26 27 have been applied to intelligent computing systems in healthcare. Papers concerning AI in the medical domain appear in many literature collections and research events, e.g., events by IEEE - Institute of Electrical and Electronics Engineers, AAAI - Conference on Artificial Intelligence, MLDM - International Conference on Machine Learning and Data Mining, or Intelligent Systems Conference, which may not be indexed in MEDLINE. However, we consider MEDLINE itself as a large enough “sample” of medical AI research to represent the fields and their interplay, so that any limitations of using only MEDLINE will not impact the results.
As mentioned, we found over 80.000 papers that were used in the field interplay analysis. However the more detailed text mining of the corpus had to be limited to the first thousand “best match” papers because of the corpus size limitations of the analytic tools. Having about 250,000 total words and over 20,000 unique word forms, size seems adequate for getting meaningful results for the phrase frequency and the collocation analysis that followed.
For the phrase frequency study, we limited the analysis to phrases occurring at least 50 times. While the tool calculated all phrase frequencies, our opinion is that there has to be a limit in order to judge that a phrase occurs sufficiently frequently in the corpus to demonstrate interest in a research field. While the limit of 50 was chosen in a somewhat arbitrary way, we think there is not much difference among little-mentioned research fields, but there is a clear difference with the leading fields that occur several hundred times. The tables and figures presented in results give some insight in what encompasses AI in the health domain and how the various areas of AI research interact.
There is no common agreement on what exactly AI encompasses; thus AI can be considered a “fuzzy” term. In the field of medicine, MeSH provides a good basis for specifying the subdomains of (medical) AI. However, MeSH includes “ knowledge representation ” as an entry term for “ artificial intelligence ”, while “ knowledge bases ” is a subcategory of AI. Outside of the medical domain, attempts to define AI and its field have led to more philosophical answers. Larry Tesler, quoted in 28 , provides a definition that may not be helpful in itself, but does highlight the hype that periodically surrounds AI, stating that “Artificial Intelligence is whatever hasn’t been done yet”. The common aspect of AI is that of computers mimicking intelligent human behavior. Whereas this is sometimes simplified as “thinking machines”, this was demonstrated being an inadequate metaphor by Edsger Dijkstra’s quote “The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.” 29 .
The results of our analysis revealed that AI research in medicine occurs in a cascading and escalating way. While neural networks, robotics, and machine learning are the research areas with the largest number of indexed publications, they show the lowest relative interplay with other areas, whereas knowledge representation publications, having one of the smallest numbers of indexed publications, expose the highest interplay of around 45%. This supports the idea that the notion of knowledge representation might play both a historical and foundational role in the various areas, providing a common cognitive layer, a still needed context, even for domains such as machine learning , neural nets , fuzzy logic , and robotics .
1 Authors, chairing the IMIA WG 6, currently called “Language and Meaning in Biomedicine”, formerly “Medical Concept Representation” are continuing the tradition of this WG time to time reaching out for a cross-disciplinary overview with other fields of biomedical information science - in this case with AI. See our WG site for more details: https://imiawg6lamb.wordpress.com/ .
IMAGES
VIDEO
COMMENTS
Abstract. How is conceptual knowledge encoded in the brain? This special issue of Cognitive Neuropsychology takes stock of current efforts to answer this question through a variety of methods and perspectives. Across this work, three questions recur, each fundamental to knowledge representation in the mind and brain.
Conceptual knowledge reflects our multi-modal 'semantic database'. As such, it brings meaning to all verbal and non-verbal stimuli, is the foundation for verbal and non-verbal expression and provides the basis for computing appropriate semantic generalizations. ... but four that relate to the nature of conceptual representations are ...
This article explores the concept of knowledge representation in AI from five distinct perspectives: surrogate, ontology, theory, computation, and expression. It argues that each role implies different demands on the representation and suggests a framework for characterizing and comparing various representation technologies.
Such influences of conceptual knowledge on perception may operate by altering the perceptual representation formed for novel objects and faces during training, or by recruiting top-down feedback from higher-order semantic to visual cortical areas, thus offsetting the perceptual demands of visual recognition (Bar et al., 2006). The latter ...
This view about the neural representation of how objects look, sound, move and so on therefore entails commitment to the idea that conceptual knowledge is a widely distributed neural network.
On one version of this approach, the concept knowledge is literally composed of more basic concepts, linked together by something like Boolean operators. Consequently, an analysis is subject not only to extensional accuracy, but to facts about the cognitive representation of knowledge and other epistemic notions. In practice, many ...
Conceptual representations in long-term memory crucially contribute to perception and action, language and thought. However, the precise nature of these conceptual memory traces is discussed controversially. ... Conceptual knowledge proper may be grounded and critically represented in sensory and motor areas, whereas the anterior temporal ...
Conceptual knowledge representation: A cross-section of current research. July 2016. Cognitive Neuropsychology 33 (3):1-9. DOI: 10.1080/02643294.2016.1188066. Authors: Timothy T Rogers. University ...
Four principles of the Conceptual Knowledge Representation Scheme emerge that help to attain effective knowledge representation. These are: 1 a focus on human comprehension only, 2 design around natural language, 3 addition of constructs common in the domain, and 4 constructs for representing abstract versions of detailed concepts. ...
Sowa describes knowledge representation as the application of logic and ontology to the task of constructing computable models for some domain. This book continues the tradition established in Sowa's first book, Conceptual structures [1], of integrating ideas from an amazing array of disciplines in a historically based, coherent, detailed, and ...
Conceptual knowledge is a self-related concept that allows us to structure our personal goals and roles. Learn how conceptual knowledge is defined and measured in different domains of mathematics, such as equivalence, cardinality, and inversion.
This chapter reviews how brain-reading studies use multivariate methods to explore the neural representation of concept knowledge in semantic memory. It addresses questions such as: What types of information are encoded in a neural concept representation? How are abstract and concrete concepts represented in the brain?
imagery can shed light on the representation of conceptual knowledge. Indeed, it is assumed that access to conceptual knowledge is necessary in order to create a mental image (e.g., Kan et al. 2003). Thus, the central question is the extent to which mental imagery relies on perceptual rep-resentations, as opposed to propositional representations.
In science education, multiple external representations such as texts, graphs, charts, or formulae are commonly used to support learners' acquisition of conceptual knowledge (Ainsworth, 2008; Corradi et al., 2012; Treagust et al., 2017).These different forms of representations provide learners with specific information about the learning object.
Learn about the key concept of knowledge representation in cognitive science and psychology, and the different types and schemas of representation. Explore the interplay between knowledge, its representation, and the physical world, and the theoretical background of semiotics and semiology.
How is conceptual knowledge encoded in the brain? This special issue of Cognitive Neuropsychology takes stock of current efforts to answer this question through a variety of methods and perspectives. Across this work, three questions recur, each fundamental to knowledge representation in the mind and brain.
Conceptual knowledge is a critical component of the learning and development (L&D) process. It refers to the understanding and comprehension of ideas, theories, principles, and concepts that are abstract and not necessarily tied to physical objects or real-world occurrences. This type of knowledge is essential in various fields, including ...
The purpose of this paper is to defend the systematic introduction of formal ontological principles in the current practice of knowledge engineering, to explore the various relationships between ontology and knowledge representation, and to present the recent trends in this promising research area. According to the "modelling view" of knowledge ...
Behavioral studies of semantic memory in the 1970s and 1980s assumed that our knowledge of the perceptual properties of everyday objects are represented by abstract or amodal symbols (e.g., Collins & Loftus, 1975; Miller & Johnson-Laird, 1976; Smith, Shoben, & Rips, 1974; Smith & Medin, 1981 ). That assumption was seriously challenged by the ...
This study examines the relation between representational competence and conceptual knowledge in female and male undergraduates using vector fields and electromagnetism as an example. It finds that representational competence is a prerequisite but not a sufficient condition for conceptual learning, and that gender affects the relation.
Learn about the field of artificial intelligence (AI) that represents information about the world in a form that a computer system can use to solve complex tasks. Explore the history, examples, and formalisms of knowledge representation and reasoning, such as semantic nets, frames, rules, logic programs and ontologies.
Humans can recognize emotions from facial expressions. Brooks and Freeman investigate the link between conceptual representation and visual perception of emotions and show that emotions that are ...
The notion of ' concept ' was a term central to what was called the field of research in ' knowledge representation'. Therefore, in order to analyze the current corpus on AI, in addition to the notion of 'knowledge representation', the notions 'language' & 'meaning' were also brought to the collocation study.