Models developed for spiking neural networks
Emergence of deep neural networks (DNNs) has raised enormous attention towards artificial neural networks (ANNs) once again. They have become the state-of-the-art models and have won different machine learning challenges. Although these networks are inspired by the brain, they lack biological plausi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016123001577 |
| _version_ | 1797796408812634112 |
|---|---|
| author | Shahriar Rezghi Shirsavar Abdol-Hossein Vahabie Mohammad-Reza A． Dehaqani |
| author_facet | Shahriar Rezghi Shirsavar Abdol-Hossein Vahabie Mohammad-Reza A． Dehaqani |
| author_sort | Shahriar Rezghi Shirsavar |
| collection | DOAJ |
| description | Emergence of deep neural networks (DNNs) has raised enormous attention towards artificial neural networks (ANNs) once again. They have become the state-of-the-art models and have won different machine learning challenges. Although these networks are inspired by the brain, they lack biological plausibility, and they have structural differences compared to the brain. Spiking neural networks (SNNs) have been around for a long time, and they have been investigated to understand the dynamics of the brain. However, their application in real-world and complicated machine learning tasks were limited. Recently, they have shown great potential in solving such tasks. Due to their energy efficiency and temporal dynamics there are many promises in their future development. In this work, we reviewed the structures and performances of SNNs on image classification tasks. The comparisons illustrate that these networks show great capabilities for more complicated problems. Furthermore, the simple learning rules developed for SNNs, such as STDP and R-STDP, can be a potential alternative to replace the backpropagation algorithm used in DNNs. • Different building blocks of spiking neural networks are explained in this work. • Developed models for SNNs are introduced based on their characteristics and building blocks. |
| first_indexed | 2024-03-13T03:33:35Z |
| format | Article |
| id | doaj.art-98d661c70d1d4a8bb936e3e6650807b8 |
| institution | Directory Open Access Journal |
| issn | 2215-0161 |
| language | English |
| last_indexed | 2024-03-13T03:33:35Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | MethodsX |
| spelling | doaj.art-98d661c70d1d4a8bb936e3e6650807b82023-06-24T05:17:33ZengElsevierMethodsX2215-01612023-01-0110102157Models developed for spiking neural networksShahriar Rezghi Shirsavar0Abdol-Hossein Vahabie1Mohammad-Reza A． Dehaqani2School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran; School of Cognitive Sciences, Institute for Research in Fundamental Sciences (IPM), Tehran, IranSchool of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IranSchool of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran; School of Cognitive Sciences, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran; Corresponding author at: School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran.Emergence of deep neural networks (DNNs) has raised enormous attention towards artificial neural networks (ANNs) once again. They have become the state-of-the-art models and have won different machine learning challenges. Although these networks are inspired by the brain, they lack biological plausibility, and they have structural differences compared to the brain. Spiking neural networks (SNNs) have been around for a long time, and they have been investigated to understand the dynamics of the brain. However, their application in real-world and complicated machine learning tasks were limited. Recently, they have shown great potential in solving such tasks. Due to their energy efficiency and temporal dynamics there are many promises in their future development. In this work, we reviewed the structures and performances of SNNs on image classification tasks. The comparisons illustrate that these networks show great capabilities for more complicated problems. Furthermore, the simple learning rules developed for SNNs, such as STDP and R-STDP, can be a potential alternative to replace the backpropagation algorithm used in DNNs. • Different building blocks of spiking neural networks are explained in this work. • Developed models for SNNs are introduced based on their characteristics and building blocks.http://www.sciencedirect.com/science/article/pii/S2215016123001577Literature review |
| spellingShingle | Shahriar Rezghi Shirsavar Abdol-Hossein Vahabie Mohammad-Reza A． Dehaqani Models developed for spiking neural networks MethodsX Literature review |
| title | Models developed for spiking neural networks |
| title_full | Models developed for spiking neural networks |
| title_fullStr | Models developed for spiking neural networks |
| title_full_unstemmed | Models developed for spiking neural networks |
| title_short | Models developed for spiking neural networks |
| title_sort | models developed for spiking neural networks |
| topic | Literature review |
| url | http://www.sciencedirect.com/science/article/pii/S2215016123001577 |
| work_keys_str_mv | AT shahriarrezghishirsavar modelsdevelopedforspikingneuralnetworks AT abdolhosseinvahabie modelsdevelopedforspikingneuralnetworks AT mohammadrezaadehaqani modelsdevelopedforspikingneuralnetworks |