86 lines
1.5 KiB
Julia
86 lines
1.5 KiB
Julia
module IronpenGPU # this is a parent module
|
||
|
||
# export
|
||
|
||
|
||
""" Order by dependencies of each file. The 1st included file must not depend on any other
|
||
files and each file can only depend on the file included before it.
|
||
"""
|
||
|
||
include("type.jl")
|
||
using .type # bring type into parent module namespace
|
||
|
||
include("snnUtil.jl")
|
||
using .snnUtil
|
||
|
||
include("forward.jl")
|
||
using .forward
|
||
|
||
include("learn.jl")
|
||
using .learn
|
||
|
||
include("interface.jl")
|
||
using .interface
|
||
|
||
|
||
#------------------------------------------------------------------------------------------------100
|
||
|
||
""" version 0.0.11
|
||
Todo:
|
||
[] make output neuron draw connection randomly
|
||
[4] implement variable dormant connection and pruning machanism. the longer the training the longer
|
||
0 weight stay 0.
|
||
[] using RL to control learning signal
|
||
[] consider using Dates.now() instead of timestamp because time_stamp may overflow
|
||
[] 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: 0.0.10
|
||
- growRepeatedPath!(), instead of synapse with 60% less activity count gets -w, may be I
|
||
should rank synapse based on activity count from highest perforimg synapse to lowest
|
||
and the last 60% of the rank get -w
|
||
- 10% instead of 20% synapticConnectionPercent
|
||
|
||
"""
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
end # module IronpenGPU
|