2019
DOI: 10.1016/j.cogsys.2018.12.016
|View full text |Cite|
|
Sign up to set email alerts
|

New ideas for brain modelling 3

Abstract: This paper describes a process for combining patterns and features, to guide a search process and make predictions. It is based on the functionality that a human brain might have, which is a highly distributed network of simple neuronal components that can apply some level of matching and cross-referencing over retrieved patterns. The process uses memory in a dynamic way and it is directed through the pattern matching. The paper firstly describes the mechanisms for neuronal search, memory and prediction. The p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
51
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
2
1

Relationship

5
2

Authors

Journals

citations
Cited by 20 publications
(51 citation statements)
references
References 52 publications
0
51
0
Order By: Relevance
“…The Concept Base has been used both for a cognitive application and as a database. For the cognitive model ( [4] and related papers), the descriptive layers might actually fit better with the symbolic neural network. This is the upper structure that is more experience-based and would process dynamic context more naturally than the knowledge-based concept tree.…”
Section: Discussionmentioning
confidence: 99%
“…The Concept Base has been used both for a cognitive application and as a database. For the cognitive model ( [4] and related papers), the descriptive layers might actually fit better with the symbolic neural network. This is the upper structure that is more experience-based and would process dynamic context more naturally than the knowledge-based concept tree.…”
Section: Discussionmentioning
confidence: 99%
“…There is clearly a problem with the design that prevents it being a universal classifier. The new classifier may also be of interest with respect to biological models of the human brain, which will be elaborated on later, but papers that note the importance of neuron links in the brain for communication processes include [19] [36]. Some of the health datasets have been tested, where a summary of the current state there can be found in [26].…”
Section: Related Workmentioning
confidence: 99%
“…A relatively new version called TopoART [19] is able to address this problem, as the shapes of the clusters do not depend on the order of creation of the associated categories. The Frequency Grid algorithm [15] that is used later, also suffers from this problem, where an improvement is suggested in section 4.2.1.…”
Section: Related Workmentioning
confidence: 99%
“…With regard to the unsupervised part, the author has published some related papers. The ensemblehierarchy model has close relations to one suggested for the cognitive model [14]- [16]. The Self-Organising Map [18] is obviously of interest, or SOM with extensions [5], as are the clustering algorithms that consider sets of closest nodes, such as DBSCAN [10], kNN or k-Means [20].…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation