utils
: Miscellaneous#
A hideous, disorganised group of utility functions. Hopefully someday they can disappear altogether or be moved elsewhere, but for now they exist, a sad blemish.
Site Navigation
Section Navigation
engine
: Differentiable enginefunctional
: Functions and functionalsactivation
: Activation functions
cmass
: Centre of mass
connectopy
: Connectopic manifolds
cov
: Covariances and correlations
fourier
: Frequency-domain filter
graph
: Graphs and networks
interpolate
: Interpolation and imputation
kernel
: Parameterised kernels
matrix
: Matrix operations
residualise
semidefinite
: Positive semidefinite cone
sparse
: Sparse matrix operations
sphere
: Spherical coordinates
sylo
: Sylo functionsymmap
: Symmetric matrix maps
tsconv
: Time series convolution
utils
: Miscellaneous
window
: Random windowing
init
: Initialisation schemesatlas
: Atlas initialisation
atlasmixins
: Atlas mixinsbase
: Base initialisations
deltaplus
dirichlet
freqfilter
: Frequency band init
iirfilter
: IIR filter initlaplace
mapparam
: Mapped parameters and parameter mapsMappedParameter
DomainMappedParameter
IdentityMappedParameter
AffineMappedParameter
TanhMappedParameter
AmplitudeTanhMappedParameter
MappedLogits
NormSphereParameter
ProbabilitySimplexParameter
AmplitudeProbabilitySimplexParameter
OrthogonalParameter
IsochoricParameter
Clip
Renormalise
ForcePositiveDefinite
PhaseAmplitudeMixin
mpbl
semidefinite
sylo
toeplitz
loss
: Loss and regularisationLoss
: Base class for scalar-valued lossesParameterisedLoss
: Extensible class for custom parameterised lossesMSELoss
: Mean squared errorNormedLoss
: Normed parameter regularisationidentity
: Identity functionzero
: Zero functiondifference
: Elementwise differenceconstraint_violation
: Soft constraintsunilateral_loss
: Unilateral penaltieshinge_loss
: SVM hinge losssmoothness
: Backwards differencesbimodal_symmetric
: Minimal distance from 2 modesdet_gram
: Gramian determinantlog_det_gram
: Gram log-determinant lossentropy
: Categorical entropykl_divergence
: Kullback-Leibler divergencejs_divergence
: Jensen-Shannon divergencebregman_divergence
: Bregman divergencesequilibrium
: Equilibrium losssecond_moment
: Second momentsauto_tol
: Significance tolerancebatch_corr
: Batch-axis correlationqcfc
: QC-FC measures and lossreference_tether
: Spatial tether to reference pointsinterhemispheric_tether
: Inter-hemispheric tethering losscompactness
: Compactnessdispersion
: Vector dispersionmultivariate_kurtosis
: Time series stationarityconnectopy
: Generalised connectopymodularity
: Relaxed modularitysum_scalarise
: Sum scalarisationmean_scalarise
: Mean scalarisationmeansq_scalarise
: Squared mean scalarisationmax_scalarise
: Maximum-value scalarisationnorm_scalarise
: Norm scalarisationvnorm_scalarise
: Vector norm scalarisationwmean_scalarise
: Weighted mean scalarisationselfwmean_scalarise
: Self-weighted mean scalarisationLossApply
: Selectively apply loss to parametersLossScheme
: Scheme for multiple lossesneuro
: Neuroscience data utilities
nn
: Neural network modules
utils
: Miscellaneous#A hideous, disorganised group of utility functions. Hopefully someday they can disappear altogether or be moved elsewhere, but for now they exist, a sad blemish.