Role of homeostasis in learning sparse representations
From MaRDI portal
Abstract: Neurons in the input layer of primary visual cortex in primates develop edge-like receptive fields. One approach to understanding the emergence of this response is to state that neural activity has to efficiently represent sensory data with respect to the statistics of natural scenes. Furthermore, it is believed that such an efficient coding is achieved using a competition across neurons so as to generate a sparse representation, that is, where a relatively small number of neurons are simultaneously active. Indeed, different models of sparse coding, coupled with Hebbian learning and homeostasis, have been proposed that successfully match the observed emergent response. However, the specific role of homeostasis in learning such sparse representations is still largely unknown. By quantitatively assessing the efficiency of the neural representation during learning, we derive a cooperative homeostasis mechanism that optimally tunes the competition between neurons within the sparse coding algorithm. We apply this homeostasis while learning small patches taken from natural images and compare its efficiency with state-of-the-art algorithms. Results show that while different sparse coding algorithms give similar coding results, the homeostasis provides an optimal balance for the representation of natural images within the population of neurons. Competition in sparse coding is optimized when it is fair. By contributing to optimizing statistical competition across neurons, homeostasis is crucial in providing a more efficient solution to the emergence of independent components.
Recommendations
- Competitive learning, natural images and cortical cells
- Hebbian Plasticity and Homeostasis in a Model of Hypercolumn of the Visual Cortex
- Bridging the functional and wiring properties of V1 neurons through sparse coding
- Hebbian learning of the statistical and geometrical structure of visual input
- Formation of pinwheels of preferred orientation by learning sparse neural representations of natural images
Cites work
- A new look at the statistical model identification
- A simplified neuron model as a principal component analyzer
- A Sparse Generative Model of V1 Simple Cells with Intrinsic Plasticity
- Blind source separation by sparse decomposition in a signal dictionary
- Could information theory provide an ecological theory of sensory processing?
- Finding independent components using spikes: A natural result of Hebbian learning in a sparse spike coding scheme
- scientific article; zbMATH DE number 1380579 (Why is no real title available?)
- Learning the parts of objects by non-negative matrix factorization
- Matching pursuits with time-frequency dictionaries
- Modeling by shortest data description
- Sparse approximation of images inspired from the functional architecture of the primary visual areas
- The problem of sparse image coding
This page was built for publication: Role of homeostasis in learning sparse representations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3576275)
