Next Article in Journal
Inefficient Eye Movements: Gamification Improves Task Execution, But Not Fixation Strategy
Previous Article in Journal
Seeing Beyond Salience and Guidance: The Role of Bias and Decision in Visual Search
Open AccessArticle

An Adaptive Homeostatic Algorithm for the Unsupervised Learning of Visual Features

INT, Inst Neurosci Timone, Aix Marseille Univ, CNRS, 27, Bd. Jean Moulin, CEDEX 5, 13385 Marseille, France
Vision 2019, 3(3), 47; https://doi.org/10.3390/vision3030047
Received: 28 June 2019 / Revised: 6 September 2019 / Accepted: 9 September 2019 / Published: 16 September 2019
The formation of structure in the visual system, that is, of the connections between cells within neural populations, is by and large an unsupervised learning process. In the primary visual cortex of mammals, for example, one can observe during development the formation of cells selective to localized, oriented features, which results in the development of a representation in area V1 of images’ edges. This can be modeled using a sparse Hebbian learning algorithms which alternate a coding step to encode the information with a learning step to find the proper encoder. A major difficulty of such algorithms is the joint problem of finding a good representation while knowing immature encoders, and to learn good encoders with a nonoptimal representation. To solve this problem, this work introduces a new regulation process between learning and coding which is motivated by the homeostasis processes observed in biology. Such an optimal homeostasis rule is implemented by including an adaptation mechanism based on nonlinear functions that balance the antagonistic processes that occur at the coding and learning time scales. It is compatible with a neuromimetic architecture and allows for a more efficient emergence of localized filters sensitive to orientation. In addition, this homeostasis rule is simplified by implementing a simple heuristic on the probability of activation of neurons. Compared to the optimal homeostasis rule, numerical simulations show that this heuristic allows to implement a faster unsupervised learning algorithm while retaining much of its effectiveness. These results demonstrate the potential application of such a strategy in machine learning and this is illustrated by showing the effect of homeostasis in the emergence of edge-like filters for a convolutional neural network.
View Full-Text
Keywords: vision; sparseness; computer vision; unsupervised learning; neuroscience vision; sparseness; computer vision; unsupervised learning; neuroscience
Show Figures

Figure 1

MDPI and ACS Style

Perrinet, L.U. An Adaptive Homeostatic Algorithm for the Unsupervised Learning of Visual Features. Vision 2019, 3, 47.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
  • Externally hosted supplementary file 1
    Link: https://spikeai.github.io/HULK/
    Description: This supplementary information presents : - first, the code to generate the figures from the paper, - second, some control experiments that were mentionned in the paper, - finally, some perspectives for future work inspired by the algorithms presented in the paper.
Back to TopTop