Struct fann::CascadeParams [−] [src]

pub struct CascadeParams {
    pub output_change_fraction: c_float,
    pub output_stagnation_epochs: c_uint,
    pub candidate_change_fraction: c_float,
    pub candidate_stagnation_epochs: c_uint,
    pub candidate_limit: fann_type,
    pub weight_multiplier: fann_type,
    pub max_out_epochs: c_uint,
    pub max_cand_epochs: c_uint,
    pub activation_functions: Vec<ActivationFunc>,
    pub activation_steepnesses: Vec<fann_type>,
    pub num_candidate_groups: c_uint,
}

Parameters for cascade training.

Fields

`output_change_fraction`	A number between 0 and 1 determining how large a fraction the mean square error should change within `output_stagnation_epochs` during training of the output connections, in order for the training to stagnate. After stagnation, training of the output connections ends and new candidates are prepared. This means: If the MSE does not change by a fraction of `output_change_fraction` during a period of `output_stagnation_epochs`, the training of the output connections is stopped because training has stagnated.
`output_stagnation_epochs`	The number of epochs training is allowed to continue without changing the MSE by a fraction of at least `output_change_fraction`.
`candidate_change_fraction`	A number between 0 and 1 determining how large a fraction the mean square error should change within `candidate_stagnation_epochs` during training of the candidate neurons, in order for the training to stagnate. After stagnation, training of the candidate neurons is stopped and the best candidate is selected. This means: If the MSE does not change by a fraction of `candidate_change_fraction` during a period of `candidate_stagnation_epochs`, the training of the candidate neurons is stopped because training has stagnated.
`candidate_stagnation_epochs`	The number of epochs training is allowed to continue without changing the MSE by a fraction of `candidate_change_fraction`.
`candidate_limit`	A limit for how much the candidate neuron may be trained. It limits the ratio between the MSE and the candidate score.
`weight_multiplier`	Multiplier for the weight of the candidate neuron before adding it to the network. Usually between 0 and 1, to make training less aggressive.
`max_out_epochs`	The maximum number of epochs the output connections may be trained after adding a new candidate neuron.
`max_cand_epochs`	The maximum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.
`activation_functions`	The activation functions for the candidate neurons.
`activation_steepnesses`	The activation function steepness values for the candidate neurons.
`num_candidate_groups`	The number of candidate neurons to be trained for each combination of activation function and steepness.

Methods

`impl CascadeParams`

`fn get_num_candidates(&self) -> c_uint`

The number of candidates used during training: the number of combinations of activation functions and steepnesses, times num_candidate_groups.

For every combination of activation function and steepness, num_candidate_groups such neurons, with different initial weights, are trained.

Trait Implementations

Struct fann::CascadeParams [−] [src]

Fields

Methods

`impl CascadeParams`

`fn get_num_candidates(&self) -> c_uint`

Trait Implementations

`impl Default for CascadeParams`

`fn default() -> CascadeParams`

Derived Implementations

`impl PartialEq for CascadeParams`

`fn eq(&self, __arg_0: &CascadeParams) -> bool`

`fn ne(&self, __arg_0: &CascadeParams) -> bool`

`impl Debug for CascadeParams`

`fn fmt(&self, __arg_0: &mut Formatter) -> Result`

`impl Clone for CascadeParams`

`fn clone(&self) -> CascadeParams`

`fn clone_from(&mut self, source: &Self)`