Open AccessProceedings Article
Replacing supervised classification learning by Slow Feature Analysis in spiking neural networks
Stefan Klampfl,Wolfgang Maass +1 more
- 07 Dec 2009
- Vol. 22, pp 988-996
TL;DR: It is demonstrated that a known unsupervised learning algorithm, Slow Feature Analysis (SFA), is able to acquire the classification capability of Fisher's Linear Discriminant (FLD), a powerful algorithm for supervised learning, if temporally adjacent samples are likely to be from the same class.
read more
Abstract: It is open how neurons in the brain are able to learn without supervision to discriminate between spatio-temporal firing patterns of presynaptic neurons. We show that a known unsupervised learning algorithm, Slow Feature Analysis (SFA), is able to acquire the classification capability of Fisher's Linear Discriminant (FLD), a powerful algorithm for supervised learning, if temporally adjacent samples are likely to be from the same class. We also demonstrate that it enables linear readout neurons of cortical microcircuits to learn the detection of repeating firing patterns within a stream of spike trains with the same firing statistics, as well as discrimination of spoken digits, in an unsupervised manner.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Unsupervised workflow discovery in industrial environments
Fabian Nater,Helmut Grabner,Luc Van Gool +2 more
- 01 Jan 2011
TL;DR: This work proposes a purely data-driven method which exploits the temporal structure of the workflow, free of human intervention and does not need parameter tuning, and shows a simple but efficient extension to analyze the image stream in real time.
Learning slow features with reservoir computing for biologically-inspired robot localization
TL;DR: This work proposes a hierarchical biologically-inspired architecture for learning sensor-based spatial representations of a robot environment in an unsupervised way, and shows that the reservoir layer is essential for learning spatial representations from low-dimensional input such as distance sensors.
Compact Classification Using the Biomimetic Properties of Ultrafast Spiking Microlaser Neurons
Gibaek Kim,Matthieu Dubernard,Sami Valentino El Nakouzi,A. Masominia,Sylvain Barbay,Laurie E. Calvet +5 more
Classification of the MNIST data set with quantum slow feature analysis
TL;DR: This work proposes a quantum version of Slow Feature Analysis (QSFA), a dimensionality reduction technique that maps the dataset in a lower dimensional space where it can apply a novel quantum classification procedure, the Quantum Frobenius Distance (QFD).
References
Real-time computing without stable states: a new framework for neural computation based on perturbations
TL;DR: A new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks, based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry.
Slow feature analysis: unsupervised learning of invariances
TL;DR: Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal that is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decor-related features, which are ordered by their degree of invariance.
Synaptic Connections and Small Circuits Involving Excitatory and Inhibitory Neurons in Layers 2–5 of Adult Rat and Cat Neocortex: Triple Intracellular Recordings and Biocytin Labelling In Vitro
TL;DR: A very high rate of connectivity was observed between pairs of interneurons, often with quite different morphologies, and the resultant IPSPs, like the EPSPs recorded in interneurs, were brief compared with those recorded in pyramidal and spiny stellate cells.
A computational model of filtering, detection, and compression in the cochlea
Richard F. Lyon
- 03 May 1982
TL;DR: This model cleanly separates these effects into time-invariant linear filtering based on a simple cascade/parallel filterbank network of second-order sections, plus transduction and compression based on half-wave rectification with a nonlinear coupled automatic gain control network.
481