CANLI
Yükleniyor Veriler getiriliyor…
/ Makaleler / Scopus Detay
Scopus YÖKSİS DOI Eşleşti SJR Q1

Neural Logic Circuits: An evolutionary neural architecture that can learn and generalize

Knowledge Based Systems · Nisan 2023

YÖKSİS DOI Eşleşmesi Bulundu

Bu Scopus makalesi YÖKSİS veritabanında da kayıtlı. Aşağıda YÖKSİS verilerini görebilirsiniz.

YÖKSİS Kayıtları
Neural Logic Circuits: An evolutionary neural architecture that can learn and generalize
Knowledge-Based Systems · 2023 SCI-Expanded
Prof. Dr. FATİH BAŞÇİFTÇİ →
YÖKSİS ISSN Eşleşmesi

Bu dergide (ISSN eşleşmesi) kurumun 2 kaydı bulundu.

YÖKSİS Kayıtları — ISSN Eşleşmesi
Discrete Artificial Algae Algorithm for solving Job-Shop Scheduling Problems
2022 ISSN: 0950-7051 SSCI Q1
Doç. Dr. MEHMET AKİF ŞAHMAN →
Neural Logic Circuits: An evolutionary neural architecture that can learn and generalize
2023 ISSN: 0950-7051 SCI-Expanded Q1
Prof. Dr. FATİH BAŞÇİFTÇİ →

Makale Bilgileri

Dergi Knowledge Based Systems
ISSN09507051
Yayın TarihiNisan 2023
Cilt / Sayfa265
DOI10.1016/j.knosys.2023.110379
Scopus ID2-s2.0-85148546346
Özet We introduce Neural Logic Circuits (NLC), an evolutionary, weightless, and learnable neural architecture loosely inspired by the neuroplasticity of the brain. This new paradigm achieves learning by evolution of its architecture through reorganization of augmenting synaptic connections and generation of artificial neurons functioning as logic gates. These neural units mimic biological nerve cells stimulated by binary input signals and emit excitatory or inhibitory pulses, thus executing the “all-or-none” character of their natural counterparts. Unlike Artificial Neural Networks (ANN), our model achieves generalization ability without intensive weight training and dedicates computational resources solely to building network architecture with optimal connectivity. We evaluated our model on well-known binary classification datasets using advanced performance metrics and compared results with modern and competitive machine learning algorithms. Extensive experimental data reveal remarkable superiority of our initial model, called NLCv1, on all test instances, achieving outstanding results for implementation of this new paradigm.

Yazarlar (2)

1
Hamit Taner Ünal
ORCID: 0000-0002-9397-8862
2
Fatih Başçiftçi

Anahtar Kelimeler

Artificial Intelligence Genetic Algorithms Logic Gates Neural Networks Neuroplasticity

Kurumlar

Selçuk Üniversitesi
Selçuklu Turkey
Scimago Dergi (ISSN Eşleşmesi)
Knowledge-Based Systems
Q1
SJR Skoru1,753
H-Index206
YayıncıElsevier B.V.
ÜlkeNetherlands
Artificial Intelligence (Q1)
Information Systems and Management (Q1)
Management Information Systems (Q1)
Software (Q1)
Dergi sayfasına git

Metrikler

5
Atıf
2
Yazar
5
Anahtar Kelime

Sistemimizdeki Yazarlar

FB
FATİH BAŞÇİFTÇİ
Prof. Dr.

Hızlı Erişim

DOI ile aç Scopus'ta aç Makaleler listesi