Feature detection using spikes: The greedy approach

@article{Perrinet2004FeatureDU,
  title={Feature detection using spikes: The greedy approach},
  author={Laurent Udo Perrinet},
  journal={Journal of Physiology-Paris},
  year={2004},
  volume={98},
  pages={530-539}
}

Figures from this paper

Efficient Source Detection Using Integrate-and-Fire Neurons
TLDR
A neuro-mimetic model of the feed-forward connections in the primary visual area (V1) solving this problem in the case where the signal may be idealized by a linear generative model using an over-complete dictionary of primitives.
Sparse spike coding : applications of neuroscience to the processing of natural images
TLDR
This paper presents in this paper their attempt at outlining the dynamical, parallel and event-based representation for vision in the architecture of the central nervous system, and will particularly focus on bridging neuroscience and image processing and on the advantages of such an interdisciplinary approach.
On efficient sparse spike coding schemes for learning natural scenes in the primary visual cortex
TLDR
It is shown that this learning algorithm based on the properties of neural computations produces adaptive and efficient representations in V1, and provides a dynamical implementation close to the concept of neural assemblies from Hebb.
Dynamical neural networks: Modeling low-level vision at short latencies
TLDR
This work proposes a simple implementation of Sparse Spike Coding using greedy inference mechanisms but also how the system may adapt in a unsupervised fashion and shows simple applications in the field of image processing as a quantitative method to evaluate these different cortical models.
A robust event-driven approach to always-on object recognition
TLDR
A neuromimetic architecture able to perform always-on pattern recognition and an analogy between the HOTS algorithm and Spiking Neural Networks (SNN) is drawn, to modify the classification layer and remodel the offline pattern categorization method previously used into an online and event-driven one.
Role of Homeostasis in Learning Sparse Representations
TLDR
By quantitatively assessing the efficiency of the neural representation during learning, a cooperative homeostasis mechanism is derived that optimally tunes the competition between neurons within the sparse coding algorithm.
Sparse Hebbian Learning is efficient with egalitarian homeostasis
TLDR
A solution based on correlation-based inhibition with a tuned egalitarian homeostasis that provides a bridge between the non-linearity of the neural response and optimal use of distributed probabilistic representations of information is proposed.
Structural information processing in early vision using Hebbian-based mean shift
TLDR
The Hebbian-based mean shift is proposed to simulate the emergence of the diversity of simple cell receptive field shapes and the robustness of the proposed algorithm in producing both Gabor-like and blob-like structors is demonstrated.
INPUT-OUTPUT TRANSFORMATION IN THE VISUO-OCULOMOTOR LOOP : MODELING THE OCULAR FOLLOWING RESPONSE TO CENTER-SURROUND STIMULATION IN A PROBABILISTIC FRAMEWORK
TLDR
Results are presented which show that the hypothesis of independence of local measures succesfully accounts for the monotonic integration of the spatial motion signal but that another mechanism must be added to account for suppressive saturation.
...
...

References

SHOWING 1-10 OF 49 REFERENCES
Finding independent components using spikes: A natural result of hebbian learning in a sparse spike coding scheme
TLDR
This work explores learning mechanisms to derive in an unsupervised manner an over-complete set of filters which provides a progressively sparser representation of the input and shows results for different strategies of representation, leading to neuro-mimetic adaptive sparse spike coding schemes.
Coding static natural images using spiking event times: do neurons Cooperate?
TLDR
Results show that this algorithm provides an efficient spike coding strategy for low-level visual processing which may adapt to the complexity of the visual input.
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
TLDR
It is shown that a learning algorithm that attempts to find sparse linear codes for natural scenes will develop a complete family of localized, oriented, bandpass receptive fields, similar to those found in the primary visual cortex.
Sparse coding with an overcomplete basis set: A strategy employed by V1?
Natural image statistics and neural representation.
TLDR
It has long been assumed that sensory neurons are adapted to the statistical properties of the signals to which they are exposed, but recent developments in statistical modeling have enabled researchers to study more sophisticated statistical models for visual images, to validate these models empirically against large sets of data, and to begin experimentally testing the efficient coding hypothesis.
A Resource-Allocating Network for Function Interpolation
TLDR
A network that allocates a new computational unit whenever an unusual pattern is presented to the network, which learns much faster than do those using backpropagation networks and uses a comparable number of synapses.
Natural signal statistics and sensory gain control
TLDR
It is shown that this decomposition, with parameters optimized for the statistics of a generic ensemble of natural images or sounds, provides a good characterization of the nonlinear response properties of typical neurons in primary visual cortex or auditory nerve, respectively.
Redundancy reduction revisited
TLDR
This paper argues that the original hypothesis was wrong in over-emphasizing the role of compressive coding and economy in neuron numbers, but right in drawing attention to the importance of redundancy.
Cortical point-spread function and long-range lateral interactions revealed by real-time optical imaging of macaque monkey primary visual cortex
TLDR
The usefulness of real-time optical imaging in the study of population activity and the exploration of cortical dendritic processing is described, raising the possibility that distributed processing over a very large cortical area plays a major role in the processing of visual information by the primary visual cortex of the primate.
...
...