docs
This commit is contained in:
@@ -25,10 +25,8 @@ using .interface
|
||||
|
||||
#------------------------------------------------------------------------------------------------100
|
||||
|
||||
""" version 0.0.2
|
||||
""" version 0.0.3
|
||||
Todo:
|
||||
[] use partial error update for computeNeuron
|
||||
[] use integrate_neuron_params synapticConnectionPercent LESS THAN 100%
|
||||
[2] implement dormant connection and pruning machanism. the longer the training the longer
|
||||
0 weight stay 0.
|
||||
[] using RL to control learning signal
|
||||
@@ -36,8 +34,10 @@ using .interface
|
||||
[] Liquid time constant. training should include adjusting α, neuron membrane potential decay factor
|
||||
which defined by neuron.tau_m formula in type.jl
|
||||
|
||||
Change from version: 0.0.1
|
||||
Change from version: 0.0.2
|
||||
- knowledgeFn in GPU format
|
||||
- use partial error update for computeNeuron
|
||||
- frequency regulator
|
||||
|
||||
All features
|
||||
|
||||
|
||||
Reference in New Issue
Block a user