refractoring

src/Ironpen.jl

@@ -0,0 +1,89 @@
+module Ironpen
+
+export kfn_1
+
+
+""" 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("types.jl")
+using .types    # bring model into this module namespace (this module is a parent module)
+
+include("snn_utils.jl")
+using .snn_utils
+
+# include("Save_and_load.jl")
+# using .Save_and_load
+
+# include("DB_services.jl")
+# using .DB_services
+
+include("forward.jl")
+using .forward
+
+include("learn.jl")
+using .learn
+
+include("readout.jl")
+using .readout
+
+include("interface.jl")
+using .interface
+#------------------------------------------------------------------------------------------------100
+
+""" 
+    Todo:
+        [*3] no "start learning" use reset learning and "inference", "learning" mode instead
+        [4] add time-based learning method. Also implement "thinking period"
+        [5] verify that model can complete learning cycle with no error
+        [6] neuroplasticity() with synaptic connection strength concept
+        [] using RL to control learning signal
+        [] consider using Dates.now() instead of timestamp because time_stamp may overflow
+        [] training should include adjusting α, neuron membrane potential decay factor
+            which defined by neuron.tau_m formular in type.jl
+
+        [DONE] each knowledgeFn should have its own noise generater
+        [DONE] where to put pseudo derivative (n.phi)
+        [DONE] add excitatory, inhabitory to neuron
+
+    Change from version:    v06_36a
+        - 
+    
+    All features
+        - multidispatch + for loop as main compute method
+        - hard connection constrain         yes
+        - normalize output                  yes
+        - allow -w_rec                      yes
+        - voltage drop when neuron fires    voltage drop equals to vth
+        - v_t decay during refractory 
+            duration                        exponantial decay
+        - input data                        population encoding, each pixel data => 
+                                                population encoding, ralative between pixel data
+        - compute neuron weight init        rand()
+        - output neuron weight init         randn()
+"""
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+end # module end