inferno.functional¶
Protocols¶
Callable used to apply bounding to the lower or upper limit of a parameter. 

Callable used to apply bounding to the lower and upper limit of a parameter. 

Callable used to interpolate in time between two tensors. 

Callable used to extrapolate in time to two tensors. 

Callable used to reduce the dimensions of a tensor. 

Callable used for computing the presynaptic or postsynaptic update of prepost training methods with spike time difference. 
Bounding¶
Computes the scaled update of power parameter dependence. 

Computes the scaled update of upperbound power parameter dependence. 

Computes the scaled update of lowerbound power parameter dependence. 

Computes the scaled update of scaled power parameter dependence. 

Computes the scaled update of upperbound scaled power parameter dependence. 

Computes the scaled update of lowerbound scaled power parameter dependence. 

Computes the scaled update of multiplicative parameter dependence. 

Computes the scaled update of upperbound multiplicative parameter dependence. 

Computes the scaled update of lowerbound multiplicative parameter dependence. 

Computes the scaled update of multiplicative parameter dependence. 

Computes the scaled update of upperbound scaled multiplicative parameter dependence. 

Computes the scaled update of lowerbound scaled multiplicative parameter dependence. 

Computes the scaled update of sharp parameter dependence. 

Computes the scaled update of upperbound sharp parameter dependence. 

Computes the scaled update of lowerbound sharp parameter dependence. 
Interpolation¶
Interpolates by selecting the previous state. 

Interpolates by selecting the next state. 

Interpolates by selecting the nearest state. 

Interpolates between previous and next states linearlly. 

Interpolates by exponentially decaying value from previous state, parameterized by a time constant. 

Interpolates by exponentially decaying value from previous state, parameterized by a rate constant. 
Extrapolation¶
Extrapolates out to the previous state. 

Extrapolates out to the next state. 

Extrapolates out to the neighboring states. 

Extrapolates out to the closest neighbor. 

Extrapolates out linearly to the next state. 

Extrapolates out linearly to the previous state. 

Extrapolates out assuming exponential decay dynamics, parameterized by a time constant. 

Extrapolates out assuming exponential decay dynamics, parameterized by a rate constant. 
Dimension Reductions¶
Returns a tensor with dimensions reduced via summation. 

Returns a tensor with dimensions reduced via summation, excluding NaN values. 

Returns a tensor with dimensions reduced via summation then divided by a constant. 

Returns a tensor with dimensions reduced via summation then divided by a constant, excluding NaN values. 

Returns a tensor with dimensions reduced by taking the minimum. 

Returns a tensor with dimensions reduced by taking the maximum. 

Returns a tensor with dimensions reduced by taking the minimum absolute distance from zero. 

Returns a tensor with dimensions reduced by taking the maximum absolute distance from zero. 

Returns a tensor with dimensions reduced by taking the arithmetic mean. 

Returns a tensor with dimensions reduced by taking the arithmetic mean, excluding NaN values. 

Returns a tensor with dimensions reduced by taking median. 

Returns a tensor with dimensions reduced by taking median, excluding NaN values. 

Returns a tensor with dimensions reduced by taking the geometric mean. 

Returns a tensor with dimensions reduced by taking the geometric mean, excluding NaN values. 

Returns a tensor with dimensions reduced by taking the arithmetic mean. 

Returns a tensor with dimensions reduced by taking the arithmetic mean, excluding NaN values. 
Spike Time Kernels¶
Returns the postsynaptic update for exponential spiketiming dependent plasticity. 

Returns the presynaptic update for exponential spiketiming dependent plasticity. 