class SHAInet::Synapse
- SHAInet::Synapse
- Reference
- Object
Defined in:
shainet/basic/synapse.crConstructors
Instance Method Summary
- #clone
- #dest_neuron : Neuron
- #dest_neuron=(dest_neuron : Neuron)
- #gradient : Float64
- #gradient=(gradient : Float64)
- #gradient_batch : Float64
- #gradient_batch=(gradient_batch : Float64)
- #gradient_sum : Float64
- #gradient_sum=(gradient_sum : Float64)
-
#inspect
Returns an unambiguous and information-rich string representation of this object, typically intended for developers.
- #m_current : Float64
- #m_current=(m_current : Float64)
- #m_prev : Float64
- #m_prev=(m_prev : Float64)
- #prev_delta : Float64
- #prev_delta=(prev_delta : Float64)
- #prev_delta_w : Float64
- #prev_delta_w=(prev_delta_w : Float64)
- #prev_gradient : Float64
- #prev_gradient=(prev_gradient : Float64)
- #prev_weight : Float64
- #prev_weight=(prev_weight : Float64)
-
#propagate_backward : Float64
Transfer error from dest_neuron to source_neuron while applying weight and save the synapse gradient
-
#propagate_forward : Float64
Transfer memory from source_neuron to dest_neuron while applying weight
- #randomize_weight
- #source_neuron : Neuron
- #source_neuron=(source_neuron : Neuron)
- #v_current : Float64
- #v_current=(v_current : Float64)
- #v_prev : Float64
- #v_prev=(v_prev : Float64)
- #weight : Float64
- #weight=(weight : Float64)
Constructor Detail
Instance Method Detail
def inspect
#
Description copied from class Object
Returns an unambiguous and information-rich string representation of this object, typically intended for developers.
This method should usually not be overridden. It delegates to
#inspect(IO) which can be overridden for custom implementations.
Also see #to_s.
def propagate_backward : Float64
#
Transfer error from dest_neuron to source_neuron while applying weight and save the synapse gradient
def propagate_forward : Float64
#
Transfer memory from source_neuron to dest_neuron while applying weight