Building Efficient Deep Hebbian Networks for Image Classification Tasks

By Yanis Bahroun, Eugénie Hunsicker, Andrea Soltoggio. 2017

11 citations recorded by the source corpus.

Multi-layer models of sparse coding (deep dictionary learning) and dimensionality reduction (PCANet) have shown promise as unsupervised learning models for image classification tasks. However, the pure implementations of these models have limited generalisation capabilities and high computational cost. This work introduces the Deep Hebbian Network (DHN), which combines the advantages of sparse coding, dimensionality reduction, and convolutional neural networks for learning features from images. Unlike in other deep neural networks, in this model, both the learning rules and neural architectures are derived from cost-function minimizations. Moreover, the DHN model can be trained online due to its Hebbian components. Different configurations of the DHN have been tested on scene and image classification tasks. Experiments show that the DHN model can automatically discover highly discriminative features directly from image pixels without using any data augmentation or semi-labeling.

Subfields: Computer Vision and Pattern Recognition, Neurology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Sebastian Risi
2. Kenneth O. Stanley
3. Andrea Soltoggio
4. Joel Lehman

In Neurology

1. Sebastian Risi
2. Kenneth O. Stanley
3. Andrea Soltoggio

Citations in the corpus

• Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “Hebbian rules have been recently proposed to minimize defined cost functions (Pehlevan et al., 2015; Bahroun et al., 2017), and more advanced systems have used backpropagation as meta-learning to tune Hebbian rules (Miconi et al.”