Package topo :: Package outputfn

Package outputfn

A family of function objects for transforming a matrix generated from some other function.

Output functions are useful for neuron activation functions, normalization of matrices, etc. They come in two varieties: OutputFunction, and CFPOutputFunction. An OutputFunction (e.g. PiecewiseLinear) applies to one matrix of any type, such as an activity matrix or a set of weights. To apply an OutputFunction to all of the weight matrices in an entire CFProjection, an OutputFunction can be plugged in to CFPOF_Plugin. CFPOF_Plugin is one example of a CFPOutputFunction, which is a function that works with the entire Projection at once.

Any new output functions added to this directory will automatically become available for any model.

$Id: __init__.py 8935 2008-08-21 13:17:58Z ceball $

Version: $Revision: 8935 $

Submodules

[hide private]

topo.outputfn.basic: Simple functions operating on a matrix, potentially modifying it.
topo.outputfn.optimized: Output functions (see basic.py) and projection-level output functions (see projfn.py) written in C to optimize performance.
topo.outputfn.projfn: Output functions (see basic.py) that apply to a whole Projection.

Classes

[hide private]

ActivityAveragingOF
Calculates the average of the input activity.

AttributeTrackingOF
Keeps track of attributes of a specified Parameterized over time, for analysis or plotting.

BinaryThreshold
Forces all values below a threshold to zero, and above it to 1.0.

DivisiveNormalizeL1
OutputFn that divides an array by its L1 norm.

DivisiveNormalizeL2
OutputFn to divide an array by its Euclidean length (aka its L2 norm).

DivisiveNormalizeLinf
OutputFn to divide an array by its L-infinity norm (i.e.

DivisiveNormalizeLp
OutputFn to divide an array by its Lp-Norm, where p is specified.

GeneralizedLogistic
The generalized logistic curve (Richards' curve): y = l + (u /(1 + b * exp(-r*(x-2*m))^(1/b))).

HalfRectify
Output function that applies a half-wave rectification (clips at zero)

HalfRectifyAndPower
Output function that applies a half-wave rectification (i.e., clips at zero), and then raises the result to the e-th power (where the exponent e can be selected arbitrarily).

HalfRectifyAndSquare
Output function that applies a half-wave rectification (clips at zero) and then squares the values.

HomeostaticMaxEnt
Implementation of homeostatic intrinsic plasticity from Jochen Triesch, ICANN 2005, LNCS 3696 pp.65-70.

IdentityOF
Identity function, returning its argument as-is.

KernelMax
Replaces the given matrix with a kernel function centered around the maximum value.

NakaRushton
Naka-Rushton curve.

OutputFn
Function object to modify a matrix in place, e.g.

OutputFnWithRandomState
Abstract base class for OutputFns that use a random number generator.

OutputFnWithState
Abstract base class for OutputFns that need to maintain a self.plastic parameter.

PatternCombine
Combine the supplied pattern with one generated using a PatternGenerator.

PiecewiseLinear
Piecewise-linear OutputFn with lower and upper thresholds.

Pipeline
Applies a list of other OutputFns in order, to combine their effects.

PipelineOF
Applies a list of other OutputFns in order, to combine their effects.

PoissonSample
Simulate Poisson-distributed activity with specified mean values.

ScalingOF
Scales input activity based on the current average activity (x_avg).

Sigmoid
Sigmoidal (logistic) output function: 1/(1+exp-(r*x+k)).

Square
Output function that applies a squaring nonlinearity.