Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks.
Συγγραφείς: Fan FL, Wang M, Dong HC, Ma J, Zeng T
Πηγή: IEEE transactions on pattern analysis and machine intelligence [IEEE Trans Pattern Anal Mach Intell] 2026 Oct; Vol. 48 (10), pp. 13759-13766.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: IEEE Computer Society Country of Publication: United States NLM ID: 9885960 Publication Model: Print Cited Medium: Internet ISSN: 1939-3539 (Electronic) Linking ISSN: 00985589 NLM ISO Abbreviation: IEEE Trans Pattern Anal Mach Intell Subsets: MEDLINE
Imprint Name(s): Original Publication: [New York] IEEE Computer Society.
Ιατρικοί όροι (MeSH): Neurons*/physiology , Neural Networks, Computer* , Models, Neurological*, Brain/physiology ; Humans ; Algorithms ; Soft Computing
Περίληψη: In the past decade, many successful networks are on novel architectures, which almost exclusively use the same type of neurons. Recently, more and more deep learning studies have been inspired by the idea of NeuroAI and the neuronal diversity observed in human brains, leading to the proposal of novel artificial neuron designs. Designing well-performing neurons represents a new dimension relative to designing well-performing neural architectures. Biologically, the brain does not rely on a single type of neuron that universally functions in all aspects. Instead, in our brain, neurons are often task-based. In this study, we address the following question: since the human brain is a task-based neuron user, can the artificial network design go from the task-based architecture design to the task-based neuron design? Since methodologically there are no one-size-fits-all neurons, given the same structure, task-based neurons can enhance the feature representation ability relative to the existing universal neurons due to the intrinsic inductive bias for the task. Specifically, we propose a two-step framework for prototyping task-based neurons. First, symbolic regression is used to identify optimal formulas that fit input data by utilizing base functions such as polynomials. We introduce vectorized symbolic regression (VSR) that stacks all variables in a vector and regularizes each input variable to perform the same computation, which can increase the regression speed, facilitate efficacy in high dimensions, and enable parallel computation. Second, we parameterize the acquired elementary formula to make parameters learnable, which serves as the aggregation function of the neuron. The activation functions such as ReLU and the sigmoidal functions remain the same because they have proven to be good. As the initial step, we evaluate the proposed framework using polynomials as base functions. Empirically, systematic experimental results on synthetic data, classic benchmarks, and real-world applications show that the proposed task-based neuron design is not only feasible but also delivers competitive performance over other state-of-the-art models.
Entry Date(s): Date Created: 20260616 Date Completed: 20260924 Latest Revision: 20260925
Update Code: 20260925
DOI: 10.1109/TPAMI.2026.3704202
PMID: 42301827
Βάση Δεδομένων: MEDLINE
FullText Links:
  – Type: other
    Url: https://resolver.ebsco.com:443/public/rma-ftfapi/ejs/direct?AccessToken=4FBD9B9BACBD10FCB8A4&Show=Object
Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 42301827
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Fan+FL%22">Fan FL</searchLink><br /><searchLink fieldCode="AU" term="%22Wang+M%22">Wang M</searchLink><br /><searchLink fieldCode="AU" term="%22Dong+HC%22">Dong HC</searchLink><br /><searchLink fieldCode="AU" term="%22Ma+J%22">Ma J</searchLink><br /><searchLink fieldCode="AU" term="%22Zeng+T%22">Zeng T</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%229885960%22">IEEE transactions on pattern analysis and machine intelligence</searchLink> [IEEE Trans Pattern Anal Mach Intell] 2026 Oct; Vol. 48 (10), pp. 13759-13766.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22IEEE+Computer+Society%22">IEEE Computer Society </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>9885960 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1939-3539 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2200985589%22">00985589 </searchLink><i>NLM ISO Abbreviation: </i>IEEE Trans Pattern Anal Mach Intell <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: [New York] IEEE Computer Society.
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Neurons%22">Neurons*</searchLink>/<searchLink fieldCode="MM" term="%22Neurons+physiology%22">physiology</searchLink> <br /><searchLink fieldCode="MM" term="%22Neural+Networks%2C+Computer%22">Neural Networks, Computer*</searchLink> <br /><searchLink fieldCode="MM" term="%22Models%2C+Neurological%22">Models, Neurological*</searchLink><br /><searchLink fieldCode="MH" term="%22Brain%22">Brain</searchLink>/<searchLink fieldCode="MH" term="%22Brain+physiology%22">physiology</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Algorithms%22">Algorithms</searchLink> ; <searchLink fieldCode="MH" term="%22Soft+Computing%22">Soft Computing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In the past decade, many successful networks are on novel architectures, which almost exclusively use the same type of neurons. Recently, more and more deep learning studies have been inspired by the idea of NeuroAI and the neuronal diversity observed in human brains, leading to the proposal of novel artificial neuron designs. Designing well-performing neurons represents a new dimension relative to designing well-performing neural architectures. Biologically, the brain does not rely on a single type of neuron that universally functions in all aspects. Instead, in our brain, neurons are often task-based. In this study, we address the following question: since the human brain is a task-based neuron user, can the artificial network design go from the task-based architecture design to the task-based neuron design? Since methodologically there are no one-size-fits-all neurons, given the same structure, task-based neurons can enhance the feature representation ability relative to the existing universal neurons due to the intrinsic inductive bias for the task. Specifically, we propose a two-step framework for prototyping task-based neurons. First, symbolic regression is used to identify optimal formulas that fit input data by utilizing base functions such as polynomials. We introduce vectorized symbolic regression (VSR) that stacks all variables in a vector and regularizes each input variable to perform the same computation, which can increase the regression speed, facilitate efficacy in high dimensions, and enable parallel computation. Second, we parameterize the acquired elementary formula to make parameters learnable, which serves as the aggregation function of the neuron. The activation functions such as ReLU and the sigmoidal functions remain the same because they have proven to be good. As the initial step, we evaluate the proposed framework using polynomials as base functions. Empirically, systematic experimental results on synthetic data, classic benchmarks, and real-world applications show that the proposed task-based neuron design is not only feasible but also delivers competitive performance over other state-of-the-art models.
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260616 <i>Date Completed: </i>20260924 <i>Latest Revision: </i>20260925
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260925
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1109/TPAMI.2026.3704202
– Name: AN
  Label: PMID
  Group: ID
  Data: 42301827
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42301827
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TPAMI.2026.3704202
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 13759
    Subjects:
      – SubjectFull: Brain physiology
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Soft Computing
        Type: general
      – SubjectFull: Neurons physiology
        Type: general
      – SubjectFull: Neural Networks, Computer
        Type: general
      – SubjectFull: Models, Neurological
        Type: general
    Titles:
      – TitleFull: No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Fan FL
      – PersonEntity:
          Name:
            NameFull: Wang M
      – PersonEntity:
          Name:
            NameFull: Dong HC
      – PersonEntity:
          Name:
            NameFull: Ma J
      – PersonEntity:
          Name:
            NameFull: Zeng T
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1939-3539
          Numbering:
            – Type: volume
              Value: 48
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: IEEE transactions on pattern analysis and machine intelligence
              Type: main
ResultId 1