Adaptation of a comprehensive simplification method to the Adaptive Exponential Integrate and Fire Neuron and Its FPGA-based verification

Bekir Şıvga; Nimet Korkmaz

Makale detayları

Adaptation of a comprehensive simplification method to the Adaptive Exponential Integrate and Fire Neuron and Its FPGA-based verification

Yazarlar:

Bekir Şıvga | Nimet Korkmaz

Yayıncı:

Nigde Omer Halisdemir University

Ana Başlıklar:

Elektronik

Dergi:

Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi Vol.14 Issue 3, pp.990-1000

Belge Tipi:

Makale

Yayın Tarihi:

7/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001354705

pISSN:

2564-6605

Anahtar kelimeler:

Özet:

 The preference of a comprehensive method usage is as important as less hardware usage on digital device-based implementations. The mathematical series expansions have a widespread usage in the transformation of expressions into simpler forms. The exponential, trigonometric, logarithmic, etc. functions are usually converted to simpler expressions for digital implementation easiness. In these implementations, it is an expected output that as the operands of the series increases, the revised model converges to the original one. However, the most appropriate number determination of these operands is important for hardware efficiency. In here, the exponential expression of the Adaptive Exponential Integrate and Fire ADEX neuron model is expanded up to the tenth operand of the Taylor series. Then, an optimum operand number is identified for getting both hardware utilization efficiency and neuronal meaningfulness. The differences between the original and revised models are compared with the error calculations and the neuronal observations. Lastly, the revised ADEX neuron model is realized by FPGA device to prove the efficiency of the proposed adaptation.

 The preference of a comprehensive method usage is as important as less hardware usage on digital device-based implementations. The mathematical series expansions have a widespread usage in the transformation of expressions into simpler forms. The exponential, trigonometric, logarithmic, etc. functions are usually converted to simpler expressions for digital implementation easiness. In these implementations, it is an expected output that as the operands of the series increases, the revised model converges to the original one. However, the most appropriate number determination of these operands is important for hardware efficiency. In here, the exponential expression of the Adaptive Exponential Integrate and Fire ADEX neuron model is expanded up to the tenth operand of the Taylor series. Then, an optimum operand number is identified for getting both hardware utilization efficiency and neuronal meaningfulness. The differences between the original and revised models are compared with the error calculations and the neuronal observations. Lastly, the revised ADEX neuron model is realized by FPGA device to prove the efficiency of the proposed adaptation.

 The preference of a comprehensive method usage is as important as less hardware usage on digital device-based implementations. The mathematical series expansions have a widespread usage in the transformation of expressions into simpler forms. The exponential, trigonometric, logarithmic, etc. functions are usually converted to simpler expressions for digital implementation easiness. In these implementations, it is an expected output that as the operands of the series increases, the revised model converges to the original one. However, the most appropriate number determination of these operands is important for hardware efficiency. In here, the exponential expression of the Adaptive Exponential Integrate and Fire ADEX neuron model is expanded up to the tenth operand of the Taylor series. Then, an optimum operand number is identified for getting both hardware utilization efficiency and neuronal meaningfulness. The differences between the original and revised models are compared with the error calculations and the neuronal observations. Lastly, the revised ADEX neuron model is realized by FPGA device to prove the efficiency of the proposed adaptation.

 Dijital cihaz tabanlı gerçekleştirimlerde kapsamlı bir yöntemin kullanılmasının tercihi, az donanım kullanımı kadar önemlidir. Matematiksel seri açılımları, ifadelerin daha basit biçimlere dönüştürülmesinde yaygın bir kullanıma sahiptir. Üstel, trigonometrik, logaritmik vb. işlevler genellikle dijital uygulama kolaylığı için daha basit ifadelere dönüştürülür. Bu uygulamalarda, serinin işlenenleri arttıkça, revize edilmiş modelin orijinal modele yakınsaması beklenen bir çıktıdır. Bununla birlikte, bu işlenenlerin en uygun sayısını belirlenmesi donanım verimliliği için önemlidir. Burada, Uyarlanabilir Üstel Entegre ve Ateşlemeli ADEX nöron modelinin üstel ifadesi, Taylor serisinin onuncu işlenenine kadar genişletilmiştir. Daha sonra, hem donanım kullanım verimliliği hem de nöronal anlamlılığı elde etmek için optimum bir işlenen sayısı belirlenmiştir. Orijinal ve revize edilmiş modeller arasındaki farklar, hata hesaplamaları ve nöronal gözlemlerle karşılaştırılmıştır. Son olarak, revize edilmiş ADEX nöron modeli, önerilen adaptasyonun verimliliğini kanıtlamak için FPGA cihazı tarafından gerçekleştirilmiştir.

Makale detayları

Adaptation of a comprehensive simplification method to the Adaptive Exponential Integrate and Fire Neuron and Its FPGA-based verification

Yazarlar:

Bekir Şıvga | Nimet Korkmaz

Yayıncı:

Nigde Omer Halisdemir University

Ana Başlıklar:

Elektronik

Dergi:

Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi Vol.14 Issue 3, pp.990-1000

Belge Tipi:

Makale

Yayın Tarihi:

7/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001354705

pISSN:

2564-6605

Adaptive exponential integrate and fire (ADEX) neuron model

Field Programmable Gate Array (FPGA)

digital implementation

neuromorphic engineering.Uyarlanabilir üstel entegre ve ateşlemeli (ADEX) nöron modeli

Alan Programlanabilir Kapı Dizisi (FPGA)

dijital gerçekleştirim

nöromorfik mühendislik.

Sayı

Makale detayları

Yazarlar: Bekir Şıvga | Nimet Korkmaz

Yayıncı: Nigde Omer Halisdemir University

Ana Başlıklar: Elektronik

Dergi: Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi Vol.14 Issue 3, pp.990-1000

Belge Tipi: Makale

Yayın Tarihi: 7/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001354705

pISSN: 2564-6605

Sayı

Yazarlar:

Bekir Şıvga | Nimet Korkmaz

Yayıncı:

Nigde Omer Halisdemir University

Ana Başlıklar:

Elektronik

Dergi:

Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi Vol.14 Issue 3, pp.990-1000

Belge Tipi:

Makale

Yayın Tarihi:

7/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001354705

pISSN:

2564-6605