The highest tagged major version is
README
¶
Docs: GoDoc
Package actrf provides activation-based receptive field computation, otherwise known as reverse correlation or spike-triggered averaging. It simply computes the activation weighted average of other source patterns of activation -- i.e., sum(act * src) / sum(src) which then shows you the patterns of source activity for which a given unit was active.
The RF's are computed and stored in 4D tensors, where the outer 2D are the 2D projection of the activation tensor (e.g., the activations of units in a layer), and the inner 2D are the 2D projection of the source tensor.
This results in a nice standard RF plot that can be visualized in a tensor grid view.
There is a standard ActRF which is cumulative over a user-defined interval and a RunningAvg version which is computed online and continuously updated but is more susceptible to sampling bias (i.e., more sampled areas are more active in general), and a recency bias.
See objrec CCN sim for example usage.
Documentation
¶
Overview ¶
Package actrf provides activation-based receptive field computation, otherwise known as reverse correlation. It simply computes the activation weighted average of other *source* patterns of activation -- i.e., sum(act * src) / sum(src) which then shows you the patterns of source activity for which a given unit was active.
The RF's are computed and stored in 4D tensors, where the outer 2D are the 2D projection of the activation tensor (e.g., the activations of units in a layer), and the inner 2D are the 2D projection of the source tensor.
This results in a nice standard RF plot that can be visualized in a tensor grid view.
There is a standard ActRF which is cumulative over a user-defined interval and a RunningAvg version which is computed online and continuously updated but is more susceptible to sampling bias (i.e., more sampled areas are more active in general), and a recency bias.
Index ¶
- func RunningAvg(out *etensor.Float32, act, src etensor.Tensor, tau float32)
- type RF
- type RFs
- func (af *RFs) Add(name string, act, src etensor.Tensor, thr float32) error
- func (af *RFs) AddRF(name string, act, src etensor.Tensor) *RF
- func (af *RFs) Avg()
- func (af *RFs) AvgNorm()
- func (af *RFs) MPISum(comm *mpi.Comm)
- func (af *RFs) Norm()
- func (af *RFs) RFByName(name string) *RF
- func (af *RFs) RFByNameTry(name string) (*RF, error)
- func (af *RFs) Reset()
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func RunningAvg ¶
RunningAvg computes a running-average activation-based receptive field for activities act relative to source activations src (the thing we're projecting rf onto) accumulating into output out, with time constant tau. act and src are projected into a 2D space (etensor.Prjn2D* methods), and resulting out is 4D of act outer and src inner.
Types ¶
type RF ¶
type RF struct {
Name string `desc:"name of this RF -- used for management of multiple in RFs"`
RF etensor.Float32 `view:"no-inline" desc:"computed receptive field, as SumProd / SumSrc -- only after Avg has been called"`
NormRF etensor.Float32 `view:"no-inline" desc:"unit normalized version of RF per source (inner 2D dimensions) -- good for display"`
NormSrc etensor.Float32 `` /* 175-byte string literal not displayed */
SumProd etensor.Float32 `view:"no-inline" desc:"sum of the products of act * src"`
SumSrc etensor.Float32 `view:"no-inline" desc:"sum of the sources (denomenator)"`
MPITmp etensor.Float32 `view:"no-inline" desc:"temporary destination sum for MPI -- only used when MPISum called"`
}
RF is used for computing an activation-based receptive field. It simply computes the activation weighted average of other *source* patterns of activation -- i.e., sum(act * src) / sum(src) which then shows you the patterns of source activity for which a given unit was active. You must call Init to initialize everything, Reset to restart the accumulation of the data, and Avg to compute the resulting averages based an accumulated data. Avg does not erase the accumulated data so it can continue beyond that point.
func (*RF) Add ¶
Add adds one sample based on activation and source tensor values. these must be of the same shape as used when Init was called. thr is a threshold value on sources below which values are not added (prevents numerical issues with very small numbers)
func (*RF) AvgNorm ¶ added in v1.3.29
func (af *RF) AvgNorm()
AvgNorm computes RF as SumProd / SumTarg and then does Norm. This is what you typically want to call before viewing RFs. Does not Reset sums.
func (*RF) Init ¶
Init initializes this RF based on name and shapes of given tensors representing the activations and source values.
func (*RF) InitShape ¶ added in v1.1.56
InitShape initializes shape for this RF based on shapes of given tensors representing the activations and source values. does nothing if shape is already correct. return shape ints
func (*RF) MPISum ¶ added in v1.3.29
MPISum aggregates RF Sum data across all processors in given mpi communicator. It adds to SumProd and SumSrc. Call this prior to calling NormAvg().
type RFs ¶
type RFs struct {
NameMap map[string]int `desc:"map of names to indexes of RFs"`
RFs []*RF `desc:"the RFs"`
}
RFs manages multiple named RF's -- each one must be initialized first but functions like Avg, Norm, and Reset can be called generically on all.
func (*RFs) AvgNorm ¶ added in v1.3.29
func (af *RFs) AvgNorm()
AvgNorm computes RF as SumProd / SumTarg and then does Norm. This is what you typically want to call before viewing RFs. Does not Reset sums.
func (*RFs) MPISum ¶ added in v1.3.29
MPISum aggregates RF Sum data across all processors in given mpi communicator. It adds to SumProd and SumSrc. Call this prior to calling NormAvg().
func (*RFs) Norm ¶
func (af *RFs) Norm()
Norm computes unit norm of RF values -- must be called after Avg
func (*RFs) RFByNameTry ¶
RFByNameTry returns RF of given name, nil and error msg if not found
Source Files