Transfer Learning for Image Classification Using Hebbian Plasticity Principles

Magotra, Arjun; Kim, Jun-Tae

doi:10.1145/3374587.3375880

Cited by 8 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed classifier, transfer learning is applied in the CNN model to improve learning efficiency [37][38][39][40]. In transfer learning, information that has been previously learned while solving a problem is transferred and reused to solve another related problem.…”

Section: Transfer Learningmentioning

confidence: 99%

Classification COVID-19 Based on Enhancement X-Ray Images and Low Complexity Model

Saad¹,

Kamil²,

Alsayat³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

has been considered one of the recent epidemics that occurred at the last of 2019 and the beginning of 2020 that world widespread. This spread of COVID-19 requires a fast technique for diagnosis to make the appropriate decision for the treatment. X-ray images are one of the most classifiable images that are used widely in diagnosing patients' data depending on radiographs due to their structures and tissues that could be classified. Convolutional Neural Networks (CNN) is the most accurate classification technique used to diagnose COVID-19 because of the ability to use a different number of convolutional layers and its high classification accuracy. Classification using CNNs techniques requires a large number of images to learn and obtain satisfactory results. In this paper, we used SqueezNet with a modified output layer to classify X-ray images into three groups: COVID-19, normal, and pneumonia. In this study, we propose a deep learning method with enhance the features of X-ray images collected from Kaggle, Figshare to distinguish between COVID-19, Normal, and Pneumonia infection. In this regard, several techniques were used on the selected image samples which are Unsharp filter, Histogram equal, and Complement image to produce another view of the dataset. The Squeeze Net CNN model has been tested in two scenarios using the 13,437 X-ray images that include 4479 for each type (COVID-19, Normal and Pneumonia). In the first scenario, the model has been tested without any enhancement on the datasets. It achieved an accuracy of 91%. But, in the second scenario, the model was tested using the same previous images after being improved by several techniques and the performance was high at approximately 95%. The conclusion of this study is the used model gives higher accuracy results for enhanced images compared with the accuracy results for the original images. A comparison of the outcomes demonstrated the effectiveness of our DL method for classifying COVID-19 based on enhanced X-ray images.

show abstract

Section: Transfer Learningmentioning

confidence: 99%

Classification COVID-19 Based on Enhancement X-Ray Images and Low Complexity Model

Saad¹,

Kamil²,

Alsayat³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Before we have mentioned the idea of combining error-driven learning with Hebbian learning in order to combine task-specific and general knowledge. This idea was also shown to be effective in the context of transfer learning [128,129] and metalearning [138], thanks to the transferability of unsupervised Hebbian features. In particular, in [138] the differentiable plasticity model was introduced, where a synapse is assumed to be composed of two parts: a backprop weight and a Hebbian weight.…”

Section: Beyond Backprop Approximationsmentioning

confidence: 99%

“…The results suggested that Hebbian learning is suitable for training early feature detectors, as well as higher network layers, but not very effective for training intermediate network layers. Furthermore, Hebbian learning was successfully used to retrain the higher layers of a pre-trained network, achieving results comparable to backprop, but requiring fewer training epochs, thus suggesting potential applications in the context of transfer learning (see also [32,156,157]). Some contributions [132,137] showed promising results of unsupervised Hebbian algorithms for semi-supervised network training, in learning scenarios with scarce data availability, achieving superior results compared to other backprop-based unsupervised methods for semi-supervised training such as Variational Auto-Encoders (VAE) [118].…”

Section: Synaptic Plasticity Models In Deep Learningmentioning

confidence: 99%

Hebbian semi-supervised learning in a sample efficiency setting

et al. 2021

View full text Add to dashboard Cite

Section: Hebbian Learningmentioning

confidence: 99%

Hebbian Semi-Supervised Learning in a Sample Efficiency Setting

Lagani,

Falchi,

Gennaro

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semisupervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and fully connected) are pre-trained using an unsupervised approach based on Hebbian learning, and the last fully connected layer (the classification layer) is trained using Stochastic Gradient Descent (SGD). In fact, as Hebbian learning is an unsupervised learning method, its potential lies in the possibility of training the internal layers of a DCNN without labeled examples. Only the final fully connected layer has to be trained with labeled examples.We performed experiments on various object recognition datasets, in different regimes of sample efficiency, comparing our semi-supervised (Hebbian for internal layers + SGD for the final fully connected layer) approach with end-to-end supervised backpropagation training. The results show that, in regimes where the number of available labeled samples is low, our semi-supervised approach outperforms full backpropagation in almost all the cases.

show abstract

Transfer Learning for Image Classification Using Hebbian Plasticity Principles

Cited by 8 publications

References 8 publications

Classification COVID-19 Based on Enhancement X-Ray Images and Low Complexity Model

Classification COVID-19 Based on Enhancement X-Ray Images and Low Complexity Model

Hebbian semi-supervised learning in a sample efficiency setting

Hebbian Semi-Supervised Learning in a Sample Efficiency Setting

Contact Info

Product

Resources

About