class NeuralNet
- NeuralNet
- Reference
- Object
Defined in:
neural_net_crystal/neural_net.crConstant Summary
-
DEFAULT_TRAINING_OPTIONS =
{max_iterations: 1000, error_threshold: 0.01}
-
MAX_STEP =
50_f64
-
MIN_STEP =
Math.exp(-6)
-
ZERO_TOLERANCE =
Math.exp(-16)
Constructors
Instance Method Summary
- #outputs : Array(Array(Float64))?
- #run(input : Array(Float64)) : Array(Float64)
- #shape : Array(Int32)
- #train(inputs, expected_outputs, opts = {} of Symbol => Float64 | Int32)
- #weight_update_values : Hash(Int32, Array(Array(Float64)))?
- #weight_update_values=(weight_update_values : Nil | Hash(Int32, Array(Array(Float64))))
- #weights : Hash(Int32, Array(Array(Float64)))?
- #weights=(weights : Nil | Hash(Int32, Array(Array(Float64))))
Constructor Detail
Instance Method Detail
def weight_update_values=(weight_update_values : Nil | Hash(Int32, Array(Array(Float64))))
#