Practical non-monotonic knowledge-base system for un-regimented domains: A Case-study in digital humanities

Pineda, Luis A.; Hernández, Noé; Torres, Ivan; Fuentes, Gibrán; Avila, Nydia Pineda De

doi:10.1016/j.ipm.2020.102214

Cited by 3 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the system can retrieve the wrong answer because it is not possible to know in advance that the query will converge due to the halting problem. This heuristic reflects analogous strategies used in symbolic representations where negation is equated with failure to proof, the so-called closed-world hypothesis, in opposition to the true or strong negation of natural language, logical languages, and knowledge-based systems supporting this kind of expressiveness 20 , 21 . These are significant differences in relation to natural memories where the distributed representation may generalize and hold patterns that have not been input explicitly; memory recovery is a constructive operation that renders a novel object; and memory reject is a sound, direct and efficient operation.…”

Section: Associative Memorymentioning

confidence: 99%

An entropic associative memory

Pineda

Fuentes

Morales

2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

Natural memories are associative, declarative and distributed, and memory retrieval is a constructive operation. In addition, cues of objects that are not contained in the memory are rejected directly. Symbolic computing memories resemble natural memories in their declarative character, and information can be stored and recovered explicitly; however, they are reproductive rather than constructive, and lack the associative and distributed properties. Sub-symbolic memories developed within the connectionist or artificial neural networks paradigm are associative and distributed, but lack the declarative property, the capability of rejecting objects that are not included in the memory, and memory retrieval is also reproductive. In this paper we present a memory model that sustains the five properties of natural memories. We use Relational-Indeterminate Computing to model associative memory registers that hold distributed representations of individual objects. This mode of computing has an intrinsic computing entropy which measures the indeterminacy of representations. This parameter determines the operational characteristics of the memory. Associative registers are embedded in an architecture that maps concrete images expressed in modality specific buffers into abstract representations and vice versa. The framework has been used to model a visual memory holding the representations of hand-written digits. The system has been tested with a set of memory recognition and retrieval experiments with complete and severely occluded images. The results show that there is a range of entropy values, not too low and not too high, in which associative memory registers have a satisfactory performance. The experiments were implemented in a simulation using a standard computer with a GPU, but a parallel architecture may be built where the memory operations would take a very reduced number of computing steps.

show abstract

Section: Associative Memorymentioning

confidence: 99%

An entropic associative memory

Pineda

Fuentes

Morales

2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Systems that never reject a cue may retrieve its most similar object within the memory, but such object is a false positive in a strict sense. If rejection does occur, a form of the so-called Closed-World Assumption (CWA) of knowledge-based system, to the effect that if a proposition cannot be proven is considered false, is adopted implicitly 10 . However, the CWA only holds if the stored knowledge is complete, in the sense that there are not facts in the world that falsify the system’s response.…”

Section: Properties Of Associative Memories and Related Workmentioning

confidence: 99%

Imagery in the entropic associative memory

Pineda¹,

Morales²

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

The Entropic Associative Memory is a novel declarative and distributed computational model of associative memory. The model is general, conceptually simple, and offers an alternative to models developed within the artificial neural networks paradigm. The memory uses a standard table as its medium, where the information is stored in an indeterminate form, and the entropy plays a functional and operation role. The memory register operation abstracts the input cue with the current memory content and is productive; memory recognition is performed through a logical test; and memory retrieval is constructive. The three operations can be performed in parallel using very few computing resources. In our previous work we explored the auto-associative properties of the memory and performed experiments to store, recognize and retrieve manuscript digits and letters with complete and incomplete cues, and also to recognize and learn phones, with satisfactory results. In such experiments a designated memory register was used to store all the objects of the same class, whereas in the present study we remove such restriction and use a single memory register to store all the objects in the domain. In this novel setting we explore the production of emerging objects and relations, such that cues are used not only to retrieve remembered objects, but also related and imaged objects, and to produce association chains. The present model supports the view that memory and classification are independent functions both conceptually and architecturally. The memory system can store images of the different modalities of perception and action, possibly multimodal, and offers a novel perspective on the imagery debate and computational models of declarative memory.

show abstract

“…* ¦ ¦ (10) The algorithm's efficiency is crucial when dealing with large-scale ontologies. The fast community partitioning algorithm can process a large amount of data in a short period of time, reducing computational costs.…”

Section: Fig 3 Basic Pattern Of Hierarchical Text Clustering Algorithmmentioning

confidence: 99%

“…In addition, the correlation between different cases is often complex, which is of great significance for students' learning, but it is difficult to demonstrate it through traditional teaching methods. Therefore, building a case knowledge base in an assisted instruction system based on a complex network can greatly promote the teaching effect of a business administration major [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Construction and Application of a Complex Network-Based Case Knowledge Base in an Assisted Instruction System

Wang,

Chang,

Ding

2023

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

With the development of the business administration major, case teaching has become an effective teaching method. However, a lot of case resources exist in the business administration field, and the correlation between these cases is complex, which poses challenges to teachers and students in terms of information overload and knowledge organization. Existing case knowledge bases in assisted instruction systems often have shortcomings in terms of knowledge relationship strength calculation, text semantic similarity calculation, hierarchical knowledge clustering, and propagation evolution. To solve these problems, this study proposed a method of constructing and applying a case knowledge base in an assisted instruction system based on a complex network. This method mainly includes three aspects: calculation and reasoning of ontology relationship strength, calculation of ontology text semantic similarity, and hierarchical knowledge clustering and propagation evolution in complex networks. Through a comprehensive study of these three aspects, a more efficient and intelligent case knowledge base in an assisted instruction system was constructed, which not only improved the teaching efficiency and quality of the business administration major but also had the potential to promote teaching in other disciplines and fields. In addition, this study also provided new perspectives and methods in related fields, which is of great significance for efficiently organizing and utilizing knowledge.

show abstract

Practical non-monotonic knowledge-base system for un-regimented domains: A Case-study in digital humanities

Cited by 3 publications

References 17 publications

An entropic associative memory

An entropic associative memory

Imagery in the entropic associative memory

Construction and Application of a Complex Network-Based Case Knowledge Base in an Assisted Instruction System

Contact Info

Product

Resources

About