Documentation
¶
Overview ¶
package kwta provides the Leabra k-Winners-Take-All inhibition function in a form that can be applied to an etensor of float32 values as computed by visual (or other modality) filtering routines.
The inhibition is computed using the FFFB feedforward-feedback function along with standard noisy-X-over-X+1 (NXX1) function that computes a resulting activation based on the inhibition.
Index ¶
- Variables
- type Chans
- type KWTA
- func (kwta *KWTA) ActFromG(geThr, ge, act float32) (nwAct, delAct float32)
- func (kwta *KWTA) Defaults()
- func (kwta *KWTA) GeThrFromG(gi float32) float32
- func (kwta *KWTA) KWTALayer(raw, act, extGi *etensor.Float32)
- func (kwta *KWTA) KWTAPool(raw, act *etensor.Float32, inhib *fffb.Inhibs, extGi *etensor.Float32)
- func (kwta *KWTA) Update()
- type NeighInhib
Constants ¶
This section is empty.
Variables ¶
var ( // ortho neighbor coordinates for 4 angles, also uses negated version // . // --- = (0,1) (X,Y) // . / // / = (-1,1) // | . = (1,0) // \ // . \ = (-1,-1) Neigh4X = []int{0, -1, 1, -1} Neigh4Y = []int{1, 1, 0, -1} )
Functions ¶
This section is empty.
Types ¶
type Chans ¶
type Chans struct {
// excitatory sodium (Na) AMPA channels activated by synaptic glutamate
E float32
// constant leak (potassium, K+) channels -- determines resting potential (typically higher than resting potential of K)
L float32
// inhibitory chloride (Cl-) channels activated by synaptic GABA
I float32
// gated / active potassium channels -- typically hyperpolarizing relative to leak / rest
K float32
}
Chans are ion channels used in computing point-neuron activation function
func (*Chans) SetFromMinusOther ¶
SetFromMinusOther sets all the values from given value minus other Chans
func (*Chans) SetFromOtherMinus ¶
SetFromOtherMinus sets all the values from other Chans minus given value
type KWTA ¶
type KWTA struct {
// whether to run kWTA or not
On bool
// maximum number of iterations to perform
Iters int
// threshold on delta-activation (change in activation) for stopping updating of activations
DelActThr float32 `default:"0.005"`
// layer-level feedforward & feedback inhibition -- applied over entire set of values
LayFFFB fffb.Params `view:"inline"`
// pool-level (feature groups) feedforward and feedback inhibition -- applied within inner-most dimensions inside outer 2 dimensions (if Pool method is called)
PoolFFFB fffb.Params `view:"inline"`
// Noisy X/X+1 rate code activation function parameters
XX1 nxx1.Params `view:"inline"`
// time constant for integrating activation
ActTau float32 `default:"3"`
// maximal conductances levels for channels
Gbar Chans `view:"inline"`
// reversal potentials for each channel
Erev Chans `view:"inline"`
// Erev - Act.Thr for each channel -- used in computing GeThrFromG among others
ErevSubThr Chans `edit:"-" view:"-"`
// Act.Thr - Erev for each channel -- used in computing GeThrFromG among others
ThrSubErev Chans `edit:"-" view:"-" json:"-" xml:"-"`
//
ActDt float32 `view:"-"; json"-" xml"-" desc:"integration rate = 1/ tau"`
}
KWTA contains all the parameters needed for computing FFFB (feedforward & feedback) inhibition that results in roughly k-Winner-Take-All behavior.
func (*KWTA) GeThrFromG ¶
GeThrFromG computes the threshold for Ge based on other conductances
func (*KWTA) KWTALayer ¶
KWTALayer computes k-Winner-Take-All activation values from raw inputs. act output tensor is set to same shape as raw inputs if not already. This version just computes a "layer" level of inhibition across the entire set of tensor values. extGi is extra / external Gi inhibition per unit -- e.g. from neighbor inhib -- must be size of raw, act.
func (*KWTA) KWTAPool ¶
KWTAPool computes k-Winner-Take-All activation values from raw inputs act output tensor is set to same shape as raw inputs if not already. This version computes both Layer and Pool (feature-group) level inibition -- tensors must be 4 dimensional -- outer 2D is Y, X Layer and inner 2D are features (pools) per location. The inhib slice is required for pool-level inhibition and will be automatically sized to outer X,Y dims if not big enough. For best performance store this and reuse to avoid memory allocations. extGi is extra / external Gi inhibition per unit -- e.g. from neighbor inhib -- must be size of raw, act.
type NeighInhib ¶
type NeighInhib struct {
// use neighborhood inhibition
On bool
// overall value of the inhibition -- this is what is added into the unit Gi inhibition level
Gi float32 `default:"0.6"`
}
NeighInhib adds an additional inhibition factor based on the same feature along an orthogonal angle -- assumes inner-most X axis represents angle of gabor or related feature. This helps reduce redundancy of feature code.
func (*NeighInhib) Defaults ¶
func (ni *NeighInhib) Defaults()
func (*NeighInhib) Inhib4 ¶
func (ni *NeighInhib) Inhib4(act, extGi *etensor.Float32)
Inhib4 computes the neighbor inhibition on activations into extGi. If extGi is not same shape as act, it will be made so (most efficient to re-use same structure). Act must be a 4D tensor with features as inner 2D. 4 version ONLY works with 4 angles (inner-most feature dimension)
Source Files