module Ai4cr::NeuralNetwork::Cmn::MiniNetConcerns::TrainAndAdjust
Direct including types
Defined in:
ai4cr/neural_network/cmn/mini_net_concerns/train_and_adjust.crInstance Method Summary
- #calculate_error_distance
- #derivative_propagation_function
- #guesses_best
- #init_net_re_train
- #input_deltas
- #input_deltas=(input_deltas)
- #last_changes
- #last_changes=(last_changes)
- #load_outputs_deltas(outputs_deltas)
- #load_outputs_expected(outputs_expected)
- #output_deltas
- #output_deltas=(output_deltas)
- #output_errors
- #output_errors=(output_errors)
- #outputs_expected
- #outputs_expected=(outputs_expected)
-
#set_deriv_scale_prelu(scale)
Per Learning Style:
- #step_backpropagate
-
#step_calc_input_deltas
Calculate deltas for hidden layers
- #step_calc_output_errors
-
#step_calculate_output_deltas
Calculate deltas for output layer
-
#step_load_chained_outputs_deltas(outputs_deltas)
This would be a chained MiniNet's input_deltas e.g.: mini_net_A feeds is chained into mini_net_B So you would mini_net_A.step_load_chained_outputs_deltas(mini_net_B.input_deltas)
- #step_load_outputs(outputs_expected)
- #step_update_weights(parallel = false)
- #step_update_weights_v1
- #step_update_weights_v2
- #train(inputs_given, outputs_expected, until_min_avg_error = UNTIL_MIN_AVG_ERROR_DEFAULT)
Instance Method Detail
def step_load_chained_outputs_deltas(outputs_deltas)
#
This would be a chained MiniNet's input_deltas e.g.: mini_net_A feeds is chained into mini_net_B So you would mini_net_A.step_load_chained_outputs_deltas(mini_net_B.input_deltas)
def train(inputs_given, outputs_expected, until_min_avg_error = UNTIL_MIN_AVG_ERROR_DEFAULT)
#