stdpneuron 0.1.8__tar.gz → 0.1.9__tar.gz

{stdpneuron-0.1.8 → stdpneuron-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: stdpneuron
-Version: 0.1.8
+Version: 0.1.9
 Summary: idk
 Project-URL: Documentation, https://github.com/Guille-ux/stdpneuron#readme
 Project-URL: Issues, https://github.com/Guille-ux/stdpneuron/issues

{stdpneuron-0.1.8 → stdpneuron-0.1.9}/src/stdpneuron/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2026-present Guille-ux <guilleleiratemes@gmail.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.1.8"
+__version__ = "0.1.9"

{stdpneuron-0.1.8 → stdpneuron-0.1.9}/src/stdpneuron/brain.py

@@ -15,6 +15,7 @@ class NeuronMass:
         self.bias = [5] * self.total_cons
         self.pr = 0
         self.outputs = [0] * self.n_neurons
+        self.last_outputs = [0] * self.n_neurons
         self.v_decay = v_decay
         self.t_decay = t_decay
     def save_model(self, name):
@@ -51,6 +52,8 @@ class NeuronMass:
                 self.connections_in[i*self.n_cons+j] = random.randint(0, self.n_neurons-1)
 		# esta función genera conexiones neuronales aleatorias, bruh	
     def tick(self):
+        self.last_outputs = self.outputs[:]
+        self.outputs = [0] * self.n_neurons
 		# PROCESAR ACTIVACIÓN DE NEURONAS
         for i in range(self.n_neurons):
             cons_ids = []
@@ -58,7 +61,7 @@ class NeuronMass:
             for j in range(self.total_cons):
                 if self.connections_in[j] == i: # es decir, esta conexión entra en la neurona q estamos mirando?
                     cons_ids.append(j)
-                    delta_voltage += self.bias[j]*self.outputs[self.connections_out[j]] * self.voltage[self.connections_out[j]]
+                    delta_voltage += self.bias[j]*self.last_outputs[self.connections_out[j]] * self.voltage[self.connections_out[j]]
                     self.temperature[j] += delta_voltage
             self.voltage[i] += delta_voltage
             if self.voltage[i] > self.threeholds[i]: