Review of Different Types of Neural Network Architectures
Innovative technologies come with such a huge amount of data that can only computerize with fast and more complex software. As time went by, more complicated problems arose such as pattern recognition, machine learning and prediction and unfortunately the conventional computer system was unable to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Teknikal Malaysia Melaka
2025-03-01
|
| Series: | International Journal of Electrical Engineering and Applied Sciences |
| Online Access: | https://ijeeas.utem.edu.my/ijeeas/article/view/6213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850277351764525056 |
|---|---|
| author | T. L. Makosso A. Almaktoof K. Abo-Al-Ez |
| author_facet | T. L. Makosso A. Almaktoof K. Abo-Al-Ez |
| author_sort | T. L. Makosso |
| collection | DOAJ |
| description |
Innovative technologies come with such a huge amount of data that can only computerize with fast and more complex software. As time went by, more complicated problems arose such as pattern recognition, machine learning and prediction and unfortunately the conventional computer system was unable to carry out such tasks. Which leads to intelligent
computational systems such as artificial neural networks. It is developed so that artificial neurons combined together would behave like a human brain. Different layers of mathematical processing are used to provide an accurate response regarding the input. Based on their architecture, training or learning methodology, and activation function, these artificial neurons are classified. The arrangement of neurons to create layers and the connections between and within the layers make up the neural network architecture. This paper aims to provide a clear and concise understanding of several types of architecture and its applications. Five mains' architectures and their applications and gaps are presented in this paper. The different architectures are: feed-forward, Convolutional and, recurrent neural networks, Auto encoder and generational encoders and Deep reinforcement learning architecture.
|
| format | Article |
| id | doaj-art-8e35284673d34c2bbd030791dc6faa75 |
| institution | OA Journals |
| issn | 2600-7495 2600-9633 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Penerbit Universiti Teknikal Malaysia Melaka |
| record_format | Article |
| series | International Journal of Electrical Engineering and Applied Sciences |
| spelling | doaj-art-8e35284673d34c2bbd030791dc6faa752025-08-20T01:49:55ZengPenerbit Universiti Teknikal Malaysia MelakaInternational Journal of Electrical Engineering and Applied Sciences2600-74952600-96332025-03-017210.54554/ijeeas.2024.7.02.006Review of Different Types of Neural Network ArchitecturesT. L. Makosso0A. Almaktoof1K. Abo-Al-Ez2Cape peninsula University of technologyCape Peninsula University of Technology (CPUT), Cape Town, South AfricaUniversity of Johannesburg, Johannesburg, South Africa Innovative technologies come with such a huge amount of data that can only computerize with fast and more complex software. As time went by, more complicated problems arose such as pattern recognition, machine learning and prediction and unfortunately the conventional computer system was unable to carry out such tasks. Which leads to intelligent computational systems such as artificial neural networks. It is developed so that artificial neurons combined together would behave like a human brain. Different layers of mathematical processing are used to provide an accurate response regarding the input. Based on their architecture, training or learning methodology, and activation function, these artificial neurons are classified. The arrangement of neurons to create layers and the connections between and within the layers make up the neural network architecture. This paper aims to provide a clear and concise understanding of several types of architecture and its applications. Five mains' architectures and their applications and gaps are presented in this paper. The different architectures are: feed-forward, Convolutional and, recurrent neural networks, Auto encoder and generational encoders and Deep reinforcement learning architecture. https://ijeeas.utem.edu.my/ijeeas/article/view/6213 |
| spellingShingle | T. L. Makosso A. Almaktoof K. Abo-Al-Ez Review of Different Types of Neural Network Architectures International Journal of Electrical Engineering and Applied Sciences |
| title | Review of Different Types of Neural Network Architectures |
| title_full | Review of Different Types of Neural Network Architectures |
| title_fullStr | Review of Different Types of Neural Network Architectures |
| title_full_unstemmed | Review of Different Types of Neural Network Architectures |
| title_short | Review of Different Types of Neural Network Architectures |
| title_sort | review of different types of neural network architectures |
| url | https://ijeeas.utem.edu.my/ijeeas/article/view/6213 |
| work_keys_str_mv | AT tlmakosso reviewofdifferenttypesofneuralnetworkarchitectures AT aalmaktoof reviewofdifferenttypesofneuralnetworkarchitectures AT kaboalez reviewofdifferenttypesofneuralnetworkarchitectures |