Deep Oscillatory Neural Network
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917771116281856 |
|---|---|
| author | Rohan, Nurani Rajagopal C, Vigneswaran Ghosh, Sayan Rajendran, Kishore A, Gaurav Chakravarthy, V Srinivasa |
| author_facet | Rohan, Nurani Rajagopal C, Vigneswaran Ghosh, Sayan Rajendran, Kishore A, Gaurav Chakravarthy, V Srinivasa |
| contents | We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal states of the network are not designed to exhibit brain-like oscillatory activity. With this motivation, the DONN is designed to have oscillatory internal dynamics. Neurons of the DONN are either nonlinear neural oscillators or traditional neurons with sigmoidal or ReLU activation. The neural oscillator used in the model is the Hopf oscillator, with the dynamics described in the complex domain. Input can be presented to the neural oscillator in three possible modes. The sigmoid and ReLU neurons also use complex-valued extensions. All the weight stages are also complex-valued. Training follows the general principle of weight change by minimizing the output error and therefore has an overall resemblance to complex backpropagation. A generalization of DONN to convolutional networks known as the Oscillatory Convolutional Neural Network is also proposed. The two proposed oscillatory networks are applied to a variety of benchmark problems in signal and image/video processing. The performance of the proposed models is either comparable or superior to published results on the same data sets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03725 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Oscillatory Neural Network Rohan, Nurani Rajagopal C, Vigneswaran Ghosh, Sayan Rajendran, Kishore A, Gaurav Chakravarthy, V Srinivasa Neural and Evolutionary Computing Artificial Intelligence Machine Learning We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal states of the network are not designed to exhibit brain-like oscillatory activity. With this motivation, the DONN is designed to have oscillatory internal dynamics. Neurons of the DONN are either nonlinear neural oscillators or traditional neurons with sigmoidal or ReLU activation. The neural oscillator used in the model is the Hopf oscillator, with the dynamics described in the complex domain. Input can be presented to the neural oscillator in three possible modes. The sigmoid and ReLU neurons also use complex-valued extensions. All the weight stages are also complex-valued. Training follows the general principle of weight change by minimizing the output error and therefore has an overall resemblance to complex backpropagation. A generalization of DONN to convolutional networks known as the Oscillatory Convolutional Neural Network is also proposed. The two proposed oscillatory networks are applied to a variety of benchmark problems in signal and image/video processing. The performance of the proposed models is either comparable or superior to published results on the same data sets. |
| title | Deep Oscillatory Neural Network |
| topic | Neural and Evolutionary Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.03725 |