Download:
by Brian S. Blais, N. Intrator, H. Shouval, Leon N Cooper
Neural Computation
http://web.bryant.edu/~bblais/pdf/neurocomp98.pdf
Add To MetaCart
Abstract:
We study several statistically and biologically motivated learning rules using the same visual environment, one made up of natural scenes, and the same single cell neuronal architecture. This allows us to concentrate on the feature extraction and neuronal coding properties of these rules. Included in these rules are kurtosis and skewness maximization, the quadratic form of the BCM learning rule, and single cell ICA. Using a structure removal method, we demonstrate that receptive fields developed using these rules depend on a small portion of the distribution. We find that the quadratic form of the BCM rule behaves in a manner similar to a kurtosis maximization rule when the distribution contains kurtotic directions, although the BCM modification equations are computationally simpler.
Citations
|
835
|
Independent component analysis: A new concept
– Comon
- 1994
|
|
710
|
An information-maximization approach to blind separation and blind deconvolution
– Bell, Sejnowski
- 1995
|
|
381
|
A new learning algorithm for blind signal separation
– Amari, Cichocki, et al.
|
|
283
|
The independent components of natural scenes are edge filters. Vision Research
– Bell, Sejnowski
- 1997
|
|
277
|
What is the goal of sensory coding
– Field
- 1994
|
|
271
|
Complete discrete 2D Gabor transform by neural networks for image analysis and compression
– Daugman
- 1988
|
|
227
|
A family of fixed-point algorithms for independent component analysis
– Hyvärinen
- 1997
|
|
171
|
Exploratory projection pursuit
– Friedman
- 1987
|
|
169
|
Theory for the development of neuron selectivity: Orientation selectivity and binocular interaction in visual cortex
– Bienenstock, Cooper, et al.
- 1982
|
|
138
|
A Projection Pursuit Algorithm for Exploratory Data Analysis
– Friedman, Tukey
- 1974
|
|
104
|
The Statistics of Natural Images
– Ruderman
- 1994
|
|
89
|
Adaptive blind separation of independent sources: a deflation approach
– Delfosse, Loubaton
- 1995
|
|
77
|
Objective function formulation of the BCM theory of visual cortical plasticity: statistical connections, stability conditions. Neural Networks 5:3–17
– Intrator, LN
- 1992
|
|
53
|
Asymptotics of graphical projection pursuit
– DIACONIS, D
- 1984
|
|
33
|
is projection pursuit ? With discussion
– Jones, Sibson
- 1987
|
|
19
|
Projection pursuit. (with discussion). The Annals of Statistics, 13:435--475
– Huber
- 1985
|
|
17
|
Energy efficient neural codes
– Levy, Baxter
- 1996
|
|
14
|
The nonlinear pca learning rule and signal separation - mathematical analysis
– Oja
- 1995
|
|
13
|
The advanced theory of statistics, volume 1
– Kendall, Stuart
- 1969
|
|
13
|
Emergence of simple cell receptive field properties by learning a sparse code for natural images. Nature
– Olshausen, Field
- 1996
|
|
10
|
A neural network for feature extraction
– Intrator
- 1990
|
|
9
|
Formation of receptive fields according to the BCM theory in realistic visual environments
– Law, Cooper
- 1994
|
|
8
|
Principal component neurons in a realistic visual environment
– Shouval, Liu
- 1996
|
|
7
|
An efficient code
– Baddeley
- 1996
|
|
3
|
Neuronal goals: Efficient coding and coincidence detection
– Intrator
- 1996
|
|
1
|
Searching for optimal visual codes: Projection pursuit analysis of the statistical structure in natural scenes
– Press, Lee
- 1996
|
