module Ai4cr::NeuralNetwork::Rnn::RnnSimpleConcerns::CalcGuess

Direct including types

Defined in:

ai4cr/neural_network/rnn/rnn_simple_concerns/calc_guess.cr

Instance Method Summary

Instance Method Detail

def bias_default : Float64 #

[View source]
def bias_default=(bias_default : Float64) #

[View source]
def bias_disabled #

[View source]
def bias_disabled=(bias_disabled) #

[View source]
def deriv_scale : Float64 #

[View source]
def deriv_scale=(deriv_scale : Float64) #

[View source]
def errors #

TODO For 'errors', research using a key of an Enum instead of String. (Using Symbol's seems incompatible with 'from_json'.)


[View source]
def eval(input_set_given) #

steps for 'eval' aka 'guess':


[View source]
def guesses_ceiled #

[View source]
def guesses_sorted #

guesses


[View source]
def guesses_top_n(n) #

[View source]
def hidden_layer_qty #

[View source]
def hidden_size #

[View source]
def hidden_size_given #

[View source]
def input_set_given #

[View source]
def input_size #

[View source]
def inputs_for(li, ti) #

[View source]
def io_offset #

The 'io_offset' param is for setting, for a given time column, how much the inputs and outputs should be offset. For example, let's say the inputs and outputs are weather data and you want to guess tomorrow's weather based on today's and the past weather. * Setting 'io_offset' value to '-1' would mean that (we're just init'ing it or...) the outputs in tc number 0 would also represent weather data for day number -1 (which would be guessing yesterday's weather, which would overlap with the input data and probably not be of much help) * Setting 'io_offset' value to '0' would mean that the outputs in tc # 0 would also represent weather data for day # 0 (straight pass-thru; not good for guessing the future, but good for translating one set of data to another, like English to Spanish or speech to text) * Setting 'io_offset' value to '1' would mean that the outputs in tc # 0 would also represent weather data for day # 1 (and would let you guess tomorrow's weather based on today's and the past weather)


[View source]
def learning_rate : Float64 #

[View source]
def learning_rate=(learning_rate : Float64) #

[View source]
def learning_styles #

[View source]
def learning_styles=(learning_styles) #

[View source]
def mini_net_set #

[View source]
def mini_net_set=(mini_net_set) #

[View source]
def momentum : Float64 #

[View source]
def momentum=(momentum : Float64) #

[View source]
def node_input_sizes #

[View source]
def node_input_sizes=(node_input_sizes) #

[View source]
def node_output_sizes #

[View source]
def node_output_sizes=(node_output_sizes) #

[View source]
def output_size #

[View source]
def outputs_guessed #

[View source]
def synaptic_layer_index_last #

[View source]
def synaptic_layer_indexes #

[View source]
def synaptic_layer_indexes_reversed #

[View source]
def synaptic_layer_qty #

[View source]
def time_col_index_last #

[View source]
def time_col_indexes #

[View source]
def time_col_indexes_reversed #

[View source]
def time_col_qty #

[View source]
def valid #

[View source]
def weight_init_scale : Float64 #

[View source]
def weight_init_scale=(weight_init_scale : Float64) #

[View source]