Investigation of Memristor-Based Neural Networks on Pattern Recognition
Mobile phones, laptops, computers, digital watches, and digital calculators are some of the most used products in our daily life. In the background, to make these gadgets work as per our desire, there are many simple components necessary for electronics to function, such as resistors, capacitors, an...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/34/1/9 |
| _version_ | 1827726261657534464 |
|---|---|
| author | Gayatri Routhu Ngangbam Phalguni Singh Selvakumar Raja Eppala Shashi Kumar Reddy |
| author_facet | Gayatri Routhu Ngangbam Phalguni Singh Selvakumar Raja Eppala Shashi Kumar Reddy |
| author_sort | Gayatri Routhu |
| collection | DOAJ |
| description | Mobile phones, laptops, computers, digital watches, and digital calculators are some of the most used products in our daily life. In the background, to make these gadgets work as per our desire, there are many simple components necessary for electronics to function, such as resistors, capacitors, and inductors, which are three basic circuit elements. The Memristor is one such component. This paper provides simulation results of the memristor circuit and its V-I characteristics at different functions as an input signal. A well-trained ANN is able to recognize images with higher precision. To enhance the properties such as accuracy, precision, and efficiency in recognition, memristor characteristics are introduced to the neural network, however, older devices experience some non-linearity issues, causing conductance-tuning problems. At the same time, to be used in some advanceable applications, ANN requires a huge amount of vector-matrix multiplication based on in-depth network expansion. An ionic floating gate (IFG) device with the characteristics of a memristive device can solve these problems. This work proposes a fully connected ANN using the IFG model, and the simulation results of the IFG model are given as synapses in deep learning. We use algorithms such as the gradient-descent model, forward and backward propagation for network building, and weight setting in neural networks to enhance their ability to recognize images. A well-trained network is formed by tuning those memristive devices to an optimized state. The synaptic memory obtained from the IFG device will be used in other deep neural networks to increase recognition accuracy. To be an activation function in the neural network, sigmoid functions were used but later replaced by the ReLu function to avoid vanishing gradients. This paper shows how images were recognized by their front, top, and side views. |
| first_indexed | 2024-03-10T22:48:35Z |
| format | Article |
| id | doaj.art-bbc3267487474f9d8091bca10d73138f |
| institution | Directory Open Access Journal |
| issn | 2673-4591 |
| language | English |
| last_indexed | 2024-03-10T22:48:35Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj.art-bbc3267487474f9d8091bca10d73138f2023-11-19T10:33:06ZengMDPI AGEngineering Proceedings2673-45912023-03-01341910.3390/HMAM2-14149Investigation of Memristor-Based Neural Networks on Pattern RecognitionGayatri Routhu0Ngangbam Phalguni Singh1Selvakumar Raja2Eppala Shashi Kumar Reddy3Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, KL Deemed to be University, Vijayawada 522302, IndiaDepartment of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, KL Deemed to be University, Vijayawada 522302, IndiaDepartment of Electronics and Communication Engineering, Anna University, Chennai 600025, IndiaDepartment of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, KL Deemed to be University, Vijayawada 522302, IndiaMobile phones, laptops, computers, digital watches, and digital calculators are some of the most used products in our daily life. In the background, to make these gadgets work as per our desire, there are many simple components necessary for electronics to function, such as resistors, capacitors, and inductors, which are three basic circuit elements. The Memristor is one such component. This paper provides simulation results of the memristor circuit and its V-I characteristics at different functions as an input signal. A well-trained ANN is able to recognize images with higher precision. To enhance the properties such as accuracy, precision, and efficiency in recognition, memristor characteristics are introduced to the neural network, however, older devices experience some non-linearity issues, causing conductance-tuning problems. At the same time, to be used in some advanceable applications, ANN requires a huge amount of vector-matrix multiplication based on in-depth network expansion. An ionic floating gate (IFG) device with the characteristics of a memristive device can solve these problems. This work proposes a fully connected ANN using the IFG model, and the simulation results of the IFG model are given as synapses in deep learning. We use algorithms such as the gradient-descent model, forward and backward propagation for network building, and weight setting in neural networks to enhance their ability to recognize images. A well-trained network is formed by tuning those memristive devices to an optimized state. The synaptic memory obtained from the IFG device will be used in other deep neural networks to increase recognition accuracy. To be an activation function in the neural network, sigmoid functions were used but later replaced by the ReLu function to avoid vanishing gradients. This paper shows how images were recognized by their front, top, and side views.https://www.mdpi.com/2673-4591/34/1/9memristormemristive deviceionic floating gate (IFG)artificial neural network (ANN)gradient descent modelforward and backward propagation |
| spellingShingle | Gayatri Routhu Ngangbam Phalguni Singh Selvakumar Raja Eppala Shashi Kumar Reddy Investigation of Memristor-Based Neural Networks on Pattern Recognition Engineering Proceedings memristor memristive device ionic floating gate (IFG) artificial neural network (ANN) gradient descent model forward and backward propagation |
| title | Investigation of Memristor-Based Neural Networks on Pattern Recognition |
| title_full | Investigation of Memristor-Based Neural Networks on Pattern Recognition |
| title_fullStr | Investigation of Memristor-Based Neural Networks on Pattern Recognition |
| title_full_unstemmed | Investigation of Memristor-Based Neural Networks on Pattern Recognition |
| title_short | Investigation of Memristor-Based Neural Networks on Pattern Recognition |
| title_sort | investigation of memristor based neural networks on pattern recognition |
| topic | memristor memristive device ionic floating gate (IFG) artificial neural network (ANN) gradient descent model forward and backward propagation |
| url | https://www.mdpi.com/2673-4591/34/1/9 |
| work_keys_str_mv | AT gayatrirouthu investigationofmemristorbasedneuralnetworksonpatternrecognition AT ngangbamphalgunisingh investigationofmemristorbasedneuralnetworksonpatternrecognition AT selvakumarraja investigationofmemristorbasedneuralnetworksonpatternrecognition AT eppalashashikumarreddy investigationofmemristorbasedneuralnetworksonpatternrecognition |