pyerualjetwork 4.2.7b0__py3-none-any.whl → 4.2.7b2__py3-none-any.whl

pyerualjetwork/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "4.2.7b0"
+__version__ = "4.2.7b2"
 __update__ = "* Changes: https://github.com/HCB06/PyerualJetwork/blob/main/CHANGES\n* PyerualJetwork Homepage: https://github.com/HCB06/PyerualJetwork/tree/main\n* PyerualJetwork document: https://github.com/HCB06/PyerualJetwork/blob/main/Welcome_to_PyerualJetwork/PYERUALJETWORK_USER_MANUEL_AND_LEGAL_INFORMATION(EN).pdf\n* YouTube tutorials: https://www.youtube.com/@HasanCanBeydili"
 
 def print_version(__version__):

pyerualjetwork/planeat.py

@@ -81,18 +81,19 @@ def evolver(weights,
             bad_genomes_selection_prob=None, 
             bar_status=True, 
             strategy='normal_selective',
-            bad_genomes_mutation_prob=None, 
-            activation_mutate_prob=0.5,  
+            bad_genomes_mutation_prob=None,
             fitness_bias=None, 
-            cross_over_mode='tpm', 
+            cross_over_mode='tpm',
             activation_mutate_add_prob=0.5, 
             activation_mutate_delete_prob=0.5, 
-            activation_mutate_change_prob=0.5, 
+            activation_mutate_change_prob=0.5,  
+            activation_selection_add_prob=0.5,
+            activation_selection_change_prob=0.5, 
+            activation_selection_threshold=2,
+            activation_mutate_prob=1,
+            activation_mutate_threshold=2,
+            weight_mutate_threshold=16,
             weight_mutate_prob=1, 
-            weight_mutate_rate=32, 
-            activation_selection_add_prob=0.6, 
-            activation_selection_change_prob=0.4, 
-            activation_selection_rate=2, 
             dtype=np.float32):
    """
    Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
@@ -145,7 +146,7 @@ def evolver(weights,
          For example, a value of 0.7 for bad genomes implies 0.3 for best genomes. Default: Determined by `policy`.
       
       activation_mutate_prob (float, optional): The probability of applying mutation to the activation functions. 
-         Must be in the range [0, 1]. Default is 0.5 (50%).
+         Must be in the range [0, 1]. Default is 1 (%100).
       
       cross_over_mode (str, optional): Specifies the crossover method to use. Options:
          - 'tpm': Two-Point Matrix Crossover.
@@ -161,21 +162,21 @@ def evolver(weights,
          Must be in the range [0, 1]. Default is 0.5.
       
       weight_mutate_prob (float, optional): The probability of mutating a weight in the genome. 
-         Must be in the range [0, 1]. Default is 1.
+         Must be in the range [0, 1]. Default is 1 (%100).
       
-      weight_mutate_rate (int, optional): If the value entered here equals the result of input_layer * output_layer, 
-         only a single weight will be mutated during each mutation process. If the value is half of the result, 
-         two weights will be mutated. WARNING: If you don't understand, do NOT change this value. Default is 32.
+      weight_mutate_threshold (int): Determines max how much weight mutaiton operation applying. (Function automaticly determines to min) Default: 16
 
       activation_selection_add_prob (float, optional): The probability of adding an existing activation function for crossover.
-         Must be in the range [0, 1]. Default is 0.6. (WARNING! Higher values increase complexity. For faster training, increase this value.)
+         Must be in the range [0, 1]. Default is 0.5. (WARNING! Higher values increase complexity. For faster training, increase this value.)
       
       activation_selection_change_prob (float, optional): The probability of changing an activation function in the genome for crossover. 
-         Must be in the range [0, 1]. Default is 0.4.
+         Must be in the range [0, 1]. Default is 0.5.
       
-      activation_selection_rate (int, optional): If the activation list of a good genome is smaller than this value, only one activation will undergo crossover. This parameter controls model complexity. Default is 2.
+      activation_mutate_threshold (int, optional): Determines max how much activation mutaiton operation applying. (Function automaticly determines to min) Default: 2
+      
+      activation_selection_threshold (int, optional): Determines max how much activaton transferable to child from undominant parent. (Function automaticly determines to min) Default: 2
 
-      dtype (numpy.dtype): Data type for the arrays. Default: np.float32. 
+      dtype (numpy.dtype, optional): Data type for the arrays. Default: np.float32. 
          Example: np.float64 or np.float16 [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not recommended!].
 
    Raises:
@@ -250,11 +251,11 @@ def evolver(weights,
    if fitness_bias < 0 or fitness_bias > 1: raise ValueError("fitness_bias value must be a number between 0 and 1.")
 
    if bad_genomes_mutation_prob is not None:
-      if not isinstance(bad_genomes_mutation_prob, float) or bad_genomes_mutation_prob < 0 or bad_genomes_mutation_prob > 1:
+      if bad_genomes_mutation_prob < 0 or bad_genomes_mutation_prob > 1:
          raise ValueError("bad_genomes_mutation_prob parameter must be float and 0-1 range")
       
    if activation_mutate_prob is not None:
-      if not isinstance(activation_mutate_prob, float) or activation_mutate_prob < 0 or activation_mutate_prob > 1:
+      if activation_mutate_prob < 0 or activation_mutate_prob > 1:
          raise ValueError("activation_mutate_prob parameter must be float and 0-1 range")
       
    if len(fitness) % 2 == 0:
@@ -321,7 +322,7 @@ def evolver(weights,
                                              cross_over_mode=cross_over_mode,
                                              activation_selection_add_prob=activation_selection_add_prob,
                                              activation_selection_change_prob=activation_selection_change_prob,
-                                             threshold=activation_selection_rate,
+                                             activation_selection_threshold=activation_selection_threshold,
                                              bad_genomes_selection_prob=bad_genomes_selection_prob,
                                              first_parent_fitness=best_fitness,
                                              fitness_bias=fitness_bias,
@@ -350,8 +351,10 @@ def evolver(weights,
                                              activation_delete_prob=activation_mutate_delete_prob, 
                                              activation_change_prob=activation_mutate_change_prob, 
                                              weight_mutate_prob=weight_mutate_prob, 
-                                             threshold=weight_mutate_rate,
-                                             genome_fitness=normalized_fitness[fitness_index]
+                                             weight_mutate_threshold=weight_mutate_threshold,
+                                             genome_fitness=normalized_fitness[fitness_index],
+                                             activation_mutate_threshold=activation_mutate_threshold,
+                                             epsilon=epsilon
                                              )
 
       if bar_status: progress.update(1)
@@ -375,15 +378,16 @@ def evolver(weights,
       print("  GOOD GENOMES MUTATION PROB: ", str(round(1 - bad_genomes_mutation_prob, 2)))
       print("  BAD GENOMES SELECTION PROB: ", str(bad_genomes_selection_prob))
       print("  WEIGHT MUTATE PROB: ", str(weight_mutate_prob))
-      print("  WEIGHT MUTATE RATE (THRESHOLD VALUE FOR SINGLE MUTATION): ", str(weight_mutate_rate))
+      print("  WEIGHT MUTATE THRESHOLD: ", str(weight_mutate_threshold))
       print("  ACTIVATION MUTATE PROB: ", str(activation_mutate_prob))
+      print("  ACTIVATION MUTATE THRESHOLD: ", str(activation_mutate_threshold))
       print("  ACTIVATION MUTATE ADD PROB: ", str(activation_mutate_add_prob))
       print("  ACTIVATION MUTATE DELETE PROB: ", str(activation_mutate_delete_prob))
       print("  ACTIVATION MUTATE CHANGE PROB: ", str(activation_mutate_change_prob))
+      print("  ACTIVATION SELECTION THRESHOLD:", str(activation_selection_threshold))
       print("  ACTIVATION SELECTION ADD PROB: ", str(activation_selection_add_prob))
       print("  ACTIVATION SELECTION CHANGE PROB: ", str(activation_selection_change_prob))
-      print("  FITNESS BIAS: ", str(fitness_bias))
-      print("  ACTIVATION SELECTION RATE (THRESHOLD VALUE FOR SINGLE CROSS OVER):", str(activation_selection_rate) + '\n')
+      print("  FITNESS BIAS: ", str(fitness_bias) + '\n')
 
 
       print("*** Performance ***")
@@ -477,7 +481,7 @@ def cross_over(first_parent_W,
                cross_over_mode,
                activation_selection_add_prob,
                activation_selection_change_prob,
-               threshold,
+               activation_selection_threshold,
                bad_genomes_selection_prob,
                first_parent_fitness,
                second_parent_fitness,
@@ -506,8 +510,7 @@ def cross_over(first_parent_W,
         activation_selection_change_prob (float): Probability of replacing an activation function in the child genome 
             with one from the second parent.
         
-        threshold (float): Determines how quickly activation functions are added or replaced 
-            during the crossover process.
+        activation_selection_threshold (float): (float): Determines max how much activaton transferable to child from undominant parent. (Function automaticly determines to min)
         
         bad_genomes_selection_prob (float): Probability of selecting a "bad" genome for replacement with the offspring.
         
@@ -539,7 +542,7 @@ def cross_over(first_parent_W,
             cross_over_mode='tpm',
             activation_selection_add_prob=0.8,
             activation_selection_change_prob=0.5,
-            threshold=2,
+            activation_selection_threshold=2,
             bad_genomes_selection_prob=0.7,
             first_parent_fitness=0.9,
             second_parent_fitness=0.85,
@@ -614,7 +617,7 @@ def cross_over(first_parent_W,
 
    if potential_activation_selection_add > activation_selection_add_prob:
       
-      threshold = abs(threshold / succes)
+      threshold = abs(activation_selection_threshold / succes)
       new_threshold = threshold
       
       while True:
@@ -661,9 +664,10 @@ def mutation(weight,
              activation_delete_prob, 
              activation_change_prob, 
              weight_mutate_prob, 
-             threshold, 
-             genome_fitness
-             ):
+             weight_mutate_threshold, 
+             genome_fitness,
+             activation_mutate_threshold,
+             epsilon):
    """
     Performs mutation on the given weight matrix and activation functions.
     - The weight matrix is mutated by randomly changing its values based on the mutation probability.
@@ -684,9 +688,13 @@ def mutation(weight,
         
         weight_mutate_prob (float): The probability of mutating weight matrix.
         
-        threshold (float): If the value you enter here is equal to the result of input layer * output layer, only a single weight will be mutated during each mutation process. If the value you enter here is half of the result of input layer * output layer, two weights in the weight matrix will be mutated.
+        weight_mutate_threshold (float): Determines max how much weight mutaiton operation applying. (Function automaticly determines to min)
         
-        genome_fitness (float): Fitness value of genome
+        genome_fitness (float): Fitness (0-1) value of genome
+
+        activation_mutate_threshold (float): Determines max how much activation mutaiton operation applying. (Function automaticly determines to min) 
+
+        epsilon (float): Small epsilon constant
 
     Returns:
         tuple: A tuple containing:
@@ -718,7 +726,7 @@ def mutation(weight,
 
       max_threshold = row_end * col_end
 
-      threshold = threshold * genome_fitness
+      threshold = weight_mutate_threshold * genome_fitness
       new_threshold = threshold
       
       for _ in range(max_threshold):
@@ -735,50 +743,64 @@ def mutation(weight,
          else:
             break
 
-   
-   activation_mutate_prob = 1 - activation_mutate_prob
-   potential_activation_mutation = random.uniform(0, 1)
+      activation_mutate_prob = 1 - activation_mutate_prob
+      potential_activation_mutation = random.uniform(0, 1)
 
-   if potential_activation_mutation > activation_mutate_prob:
-      
-      except_this = ['spiral', 'circular']
-      all_acts = [item for item in all_activations() if item not in except_this] # SPIRAL AND CIRCULAR ACTIVATION DISCARDED
-      
-      activation_add_prob = 1 - activation_add_prob
-      activation_delete_prob = 1 - activation_delete_prob
-      activation_change_prob = 1 - activation_change_prob
+      if potential_activation_mutation > activation_mutate_prob:
+            
+         genome_fitness += epsilon
+         threshold = abs(activation_mutate_threshold / genome_fitness)
+         max_threshold = len(activations)
 
-      potential_activation_add_prob = random.uniform(0, 1)
-      potential_activation_delete_prob = random.uniform(0, 1)
-      potential_activation_change_prob = random.uniform(0, 1)
+         new_threshold = threshold
 
-      if potential_activation_add_prob > activation_add_prob:
+         except_this = ['spiral', 'circular']
+         all_acts = [item for item in all_activations() if item not in except_this] # SPIRAL AND CIRCULAR ACTIVATION DISCARDED
+         
+         activation_add_prob = 1 - activation_add_prob
+         activation_delete_prob = 1 - activation_delete_prob
+         activation_change_prob = 1 - activation_change_prob
 
-         try:
-            
-            random_index_all_act = int(random.uniform(0, len(all_acts)-1))
-            activations.append(all_acts[random_index_all_act])
+         for _ in range(max_threshold):
 
-         except:
+            potential_activation_add_prob = random.uniform(0, 1)
+            potential_activation_delete_prob = random.uniform(0, 1)
+            potential_activation_change_prob = random.uniform(0, 1)
 
-            activation = activations
-            activations = []
 
-            activations.append(activation)
-            activations.append(all_acts[int(random.uniform(0, len(all_acts)-1))])
-            
-      if potential_activation_delete_prob > activation_delete_prob and len(activations) > 1:
-         
-         random_index = random.randint(0, len(activations) - 1)
-         activations.pop(random_index)
-         
-         
-      if potential_activation_change_prob > activation_change_prob:
-         
-         random_index_all_act = int(random.uniform(0, len(all_acts)-1))
-         random_index_genom_act = int(random.uniform(0, len(activations)-1))
+            if potential_activation_delete_prob > activation_delete_prob and len(activations) > 1:
+               
+               random_index = random.randint(0, len(activations) - 1)
+               activations.pop(random_index)
+
+
+            if potential_activation_add_prob > activation_add_prob:
+
+               try:
+                  
+                  random_index_all_act = int(random.uniform(0, len(all_acts)-1))
+                  activations.append(all_acts[random_index_all_act])
+
+               except:
+
+                  activation = activations
+                  activations = []
+
+                  activations.append(activation)
+                  activations.append(all_acts[int(random.uniform(0, len(all_acts)-1))])
+               
+               
+            if potential_activation_change_prob > activation_change_prob:
+               
+               random_index_all_act = int(random.uniform(0, len(all_acts)-1))
+               random_index_genom_act = int(random.uniform(0, len(activations)-1))
+
+               activations[random_index_genom_act] = all_acts[random_index_all_act]
+
+            new_threshold += threshold
 
-         activations[random_index_genom_act] = all_acts[random_index_all_act]
+            if max_threshold > new_threshold: pass
+            else: break
 
    return weight, activations
 

pyerualjetwork/planeat_cuda.py

@@ -83,18 +83,19 @@ def evolver(weights,
             bad_genomes_selection_prob=None, 
             bar_status=True, 
             strategy='normal_selective',
-            bad_genomes_mutation_prob=None, 
-            activation_mutate_prob=0.5, 
+            bad_genomes_mutation_prob=None,  
             fitness_bias=None, 
             cross_over_mode='tpm',
             activation_mutate_add_prob=0.5, 
             activation_mutate_delete_prob=0.5, 
-            activation_mutate_change_prob=0.5, 
+            activation_mutate_change_prob=0.5,  
+            activation_selection_add_prob=0.5,
+            activation_selection_change_prob=0.5, 
+            activation_selection_threshold=2,
+            activation_mutate_prob=1,
+            activation_mutate_threshold=2,
+            weight_mutate_threshold=16,
             weight_mutate_prob=1, 
-            weight_mutate_rate=32, 
-            activation_selection_add_prob=0.6, 
-            activation_selection_change_prob=0.4, 
-            activation_selection_rate=2, 
             dtype=cp.float32):
    """
   Applies the evolving process of a population of genomes using selection, crossover, mutation, and activation function potentiation.
@@ -165,17 +166,17 @@ def evolver(weights,
       weight_mutate_prob (float, optional): The probability of mutating a weight in the genome. 
          Must be in the range [0, 1]. Default is 1.
       
-      weight_mutate_rate (int, optional): If the value entered here equals the result of input_layer * output_layer, 
-         only a single weight will be mutated during each mutation process. If the value is half of the result, 
-         two weights will be mutated. WARNING: If you don't understand, do NOT change this value. Default is 32.
+      weight_mutate_threshold (int): Determines max how much weight mutaiton operation applying. (Function automaticly determines to min) Default: 16
 
       activation_selection_add_prob (float, optional): The probability of adding an existing activation function for crossover.
-         Must be in the range [0, 1]. Default is 0.6. (WARNING! Higher values increase complexity. For faster training, increase this value.)
+         Must be in the range [0, 1]. Default is 0.5. (WARNING! Higher values increase complexity. For faster training, increase this value.)
       
       activation_selection_change_prob (float, optional): The probability of changing an activation function in the genome for crossover. 
-         Must be in the range [0, 1]. Default is 0.4.
+         Must be in the range [0, 1]. Default is 0.5.
+      
+      activation_mutate_threshold (int): Determines max how much activation mutaiton operation applying. (Function automaticly determines to min) Default: 2
       
-      activation_selection_rate (int, optional): If the activation list of a good genome is smaller than this value, only one activation will undergo crossover. This parameter controls model complexity. Default is 2.
+      activation_selection_threshold (int, optional): Determines max how much activaton transferable to child from undominant parent. (Function automaticly determines to min) Default: 2
 
       dtype (cupy.dtype): Data type for the arrays. Default: cp.float32. 
          Example: cp.float64 or cp.float16 [fp32 for balanced devices, fp64 for strong devices, fp16 for weak devices: not recommended!].
@@ -251,11 +252,11 @@ def evolver(weights,
    if fitness_bias < 0 or fitness_bias > 1: raise ValueError("fitness_bias value must be a number between 0 and 1.")
 
    if bad_genomes_mutation_prob is not None:
-      if not isinstance(bad_genomes_mutation_prob, float) or bad_genomes_mutation_prob < 0 or bad_genomes_mutation_prob > 1:
+      if bad_genomes_mutation_prob < 0 or bad_genomes_mutation_prob > 1:
          raise ValueError("bad_genomes_mutation_prob parameter must be float and 0-1 range")
       
    if activation_mutate_prob is not None:
-      if not isinstance(activation_mutate_prob, float) or activation_mutate_prob < 0 or activation_mutate_prob > 1:
+      if activation_mutate_prob < 0 or activation_mutate_prob > 1:
          raise ValueError("activation_mutate_prob parameter must be float and 0-1 range")
       
    if len(fitness) % 2 == 0:
@@ -322,7 +323,7 @@ def evolver(weights,
                                              cross_over_mode=cross_over_mode,
                                              activation_selection_add_prob=activation_selection_add_prob,
                                              activation_selection_change_prob=activation_selection_change_prob,
-                                             threshold=activation_selection_rate,
+                                             activation_selection_threshold=activation_selection_threshold,
                                              bad_genomes_selection_prob=bad_genomes_selection_prob,
                                              first_parent_fitness=best_fitness,
                                              fitness_bias=fitness_bias,
@@ -351,8 +352,10 @@ def evolver(weights,
                                              activation_delete_prob=activation_mutate_delete_prob, 
                                              activation_change_prob=activation_mutate_change_prob, 
                                              weight_mutate_prob=weight_mutate_prob, 
-                                             threshold=weight_mutate_rate,
-                                             genome_fitness=normalized_fitness[fitness_index]
+                                             weight_mutate_threshold=weight_mutate_threshold,
+                                             genome_fitness=normalized_fitness[fitness_index],
+                                             activation_mutate_threshold=activation_mutate_threshold,
+                                             epsilon=epsilon
                                              )
             
       if bar_status: progress.update(1)
@@ -374,17 +377,19 @@ def evolver(weights,
       print("  POLICY: ", policy)
       print("  BAD GENOMES MUTATION PROB: ", str(bad_genomes_mutation_prob))
       print("  GOOD GENOMES MUTATION PROB: ", str(round(1 - bad_genomes_mutation_prob, 2)))
+      print("  BAD GENOMES SELECTION PROB: ", str(bad_genomes_selection_prob))
       print("  WEIGHT MUTATE PROB: ", str(weight_mutate_prob))
-      print("  WEIGHT MUTATE RATE (THRESHOLD VALUE FOR SINGLE MUTATION): ", str(weight_mutate_rate))
+      print("  WEIGHT MUTATE THRESHOLD: ", str(weight_mutate_threshold))
       print("  ACTIVATION MUTATE PROB: ", str(activation_mutate_prob))
+      print("  ACTIVATION MUTATE THRESHOLD: ", str(activation_mutate_threshold))
       print("  ACTIVATION MUTATE ADD PROB: ", str(activation_mutate_add_prob))
       print("  ACTIVATION MUTATE DELETE PROB: ", str(activation_mutate_delete_prob))
       print("  ACTIVATION MUTATE CHANGE PROB: ", str(activation_mutate_change_prob))
+      print("  ACTIVATION SELECTION THRESHOLD:", str(activation_selection_threshold))
       print("  ACTIVATION SELECTION ADD PROB: ", str(activation_selection_add_prob))
       print("  ACTIVATION SELECTION CHANGE PROB: ", str(activation_selection_change_prob))
-      print("  FITNESS BIAS: ", str(fitness_bias))
-      print("  ACTIVATION SELECTION RATE (THRESHOLD VALUE FOR SINGLE CROSS OVER):", str(activation_selection_rate) + '\n')
-      
+      print("  FITNESS BIAS: ", str(fitness_bias) + '\n')
+
       print("*** Performance ***")
       print("  MAX FITNESS: ", str(cp.round(max(fitness), 2)))
       print("  MEAN FITNESS: ", str(cp.round(cp.mean(fitness), 2)))
@@ -480,7 +485,7 @@ def cross_over(first_parent_W,
                cross_over_mode,
                activation_selection_add_prob,
                activation_selection_change_prob,
-               threshold,
+               activation_selection_threshold,
                bad_genomes_selection_prob,
                first_parent_fitness,
                second_parent_fitness,
@@ -509,8 +514,7 @@ def cross_over(first_parent_W,
         activation_selection_change_prob (float): Probability of replacing an activation function in the child genome 
             with one from the second parent.
         
-        threshold (float): Determines how quickly activation functions are added or replaced 
-            during the crossover process.
+        activation_selection_threshold (int): Determines max how much activaton transferable to child from undominant parent. (Function automaticly determines to min)
         
         bad_genomes_selection_prob (float): Probability of selecting a "bad" genome for replacement with the offspring.
         
@@ -542,7 +546,7 @@ def cross_over(first_parent_W,
             cross_over_mode='tpm',
             activation_selection_add_prob=0.8,
             activation_selection_change_prob=0.5,
-            threshold=2,
+            activation_selection_threshold=2,
             bad_genomes_selection_prob=0.7,
             first_parent_fitness=0.9,
             second_parent_fitness=0.85,
@@ -618,7 +622,7 @@ def cross_over(first_parent_W,
 
    if potential_activation_selection_add > activation_selection_add_prob:
       
-      threshold = abs(threshold / succes)
+      threshold = abs(activation_selection_threshold / succes)
       new_threshold = threshold
       
       while True:
@@ -668,8 +672,10 @@ def mutation(weight,
              activation_delete_prob, 
              activation_change_prob, 
              weight_mutate_prob, 
-             threshold, 
-             genome_fitness):
+             weight_mutate_threshold, 
+             genome_fitness,
+             activation_mutate_threshold,
+             epsilon):
    """
     Performs mutation on the given weight matrix and activation functions.
     - The weight matrix is mutated by randomly changing its values based on the mutation probability.
@@ -690,10 +696,13 @@ def mutation(weight,
         
         weight_mutate_prob (float): The probability of mutating weight matrix.
         
-        threshold (float): If the value you enter here is equal to the result of input layer * output layer, only a single weight will be mutated during each mutation process. If the value you enter here is half of the result of input layer * output layer, two weights in the weight matrix will be mutated.
+        weight_mutate_threshold (float): Determines max how much weight mutaiton operation applying. (Function automaticly determines to min)
         
         genome_fitness (float): Fitness value of genome
     
+        activation_mutate_threshold (float): Determines max how much activation mutaiton operation applying. (Function automaticly determines to min) 
+
+        epsilon (float): Small epsilon constant
 
     Returns:
         tuple: A tuple containing:
@@ -725,7 +734,7 @@ def mutation(weight,
       
       max_threshold = row_end * col_end
 
-      threshold = threshold * genome_fitness
+      threshold = weight_mutate_threshold * genome_fitness
       new_threshold = threshold
 
       for _ in range(max_threshold):
@@ -741,50 +750,64 @@ def mutation(weight,
          
          else:
             break
-   
-   activation_mutate_prob = 1 - activation_mutate_prob
-   potential_activation_mutation = random.uniform(0, 1)
 
-   if potential_activation_mutation > activation_mutate_prob:
-      
-      except_this = ['spiral', 'circular']
-      all_acts = [item for item in all_activations() if item not in except_this] # SPIRAL AND CIRCULAR ACTIVATION DISCARDED
-      
-      activation_add_prob = 1 - activation_add_prob
-      activation_delete_prob = 1 - activation_delete_prob
-      activation_change_prob = 1 - activation_change_prob
+      activation_mutate_prob = 1 - activation_mutate_prob
+      potential_activation_mutation = random.uniform(0, 1)
 
-      potential_activation_add_prob = random.uniform(0, 1)
-      potential_activation_delete_prob = random.uniform(0, 1)
-      potential_activation_change_prob = random.uniform(0, 1)
+      if potential_activation_mutation > activation_mutate_prob:
+         
+         genome_fitness += epsilon
+         threshold = abs(activation_mutate_threshold / genome_fitness)
+         max_threshold = len(activations)
 
-      if potential_activation_add_prob > activation_add_prob:
+         new_threshold = threshold
 
-         try:
-            
-            random_index_all_act = int(random.uniform(0, len(all_acts)-1))
-            activations.append(all_acts[random_index_all_act])
+         except_this = ['spiral', 'circular']
+         all_acts = [item for item in all_activations() if item not in except_this] # SPIRAL AND CIRCULAR ACTIVATION DISCARDED
+         
+         activation_add_prob = 1 - activation_add_prob
+         activation_delete_prob = 1 - activation_delete_prob
+         activation_change_prob = 1 - activation_change_prob
 
-         except:
+         for _ in range(max_threshold):
 
-            activation = activations
-            activations = []
+            potential_activation_add_prob = random.uniform(0, 1)
+            potential_activation_delete_prob = random.uniform(0, 1)
+            potential_activation_change_prob = random.uniform(0, 1)
 
-            activations.append(activation)
-            activations.append(all_acts[int(random.uniform(0, len(all_acts)-1))])
             
-      if potential_activation_delete_prob > activation_delete_prob and len(activations) > 1:
-         
-         random_index = random.randint(0, len(activations) - 1)
-         activations.pop(random_index)
-         
-         
-      if potential_activation_change_prob > activation_change_prob:
-         
-         random_index_all_act = int(random.uniform(0, len(all_acts)-1))
-         random_index_genom_act = int(random.uniform(0, len(activations)-1))
+            if potential_activation_delete_prob > activation_delete_prob and len(activations) > 1:
+               
+               random_index = random.randint(0, len(activations) - 1)
+               activations.pop(random_index)
+               
+
+            if potential_activation_add_prob > activation_add_prob:
+
+               try:
+                  
+                  random_index_all_act = int(random.uniform(0, len(all_acts)-1))
+                  activations.append(all_acts[random_index_all_act])
+
+               except:
+
+                  activation = activations
+                  activations = []
+
+                  activations.append(activation)
+                  activations.append(all_acts[int(random.uniform(0, len(all_acts)-1))])
+               
+            if potential_activation_change_prob > activation_change_prob:
+               
+               random_index_all_act = int(random.uniform(0, len(all_acts)-1))
+               random_index_genom_act = int(random.uniform(0, len(activations)-1))
+
+               activations[random_index_genom_act] = all_acts[random_index_all_act]
+
+            new_threshold += threshold
 
-         activations[random_index_genom_act] = all_acts[random_index_all_act]
+            if max_threshold > new_threshold: pass
+            else: break
 
    return weight, activations
 

{pyerualjetwork-4.2.7b0.dist-info → pyerualjetwork-4.2.7b2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyerualjetwork
-Version: 4.2.7b0
+Version: 4.2.7b2
 Summary: PyerualJetwork is a machine learning library supported with GPU(CUDA) acceleration written in Python for professionals and researchers including with PLAN algorithm, PLANEAT algorithm (genetic optimization). Also includes data pre-process and memory manegament
 Author: Hasan Can Beydili
 Author-email: tchasancan@gmail.com

{pyerualjetwork-4.2.7b0.dist-info → pyerualjetwork-4.2.7b2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pyerualjetwork/__init__.py,sha256=ATsdY6XagZY8d3RYpOmbFb_FXtIG2nPE8V_KgIBAeDs,641
+pyerualjetwork/__init__.py,sha256=R2t2Y9xGH2tGKw-ccl-sjVrHEqYcvp0timRkvKZCbxE,641
 pyerualjetwork/activation_functions.py,sha256=WWOdMd5pI6ZKe-ieKCIsKAYPQODHuXYxx7tzhA5xjes,11767
 pyerualjetwork/activation_functions_cuda.py,sha256=KmXJ5Cdig46XAMYakXFPEOlxSxtFJjD21-i3nGtxPjE,11807
 pyerualjetwork/data_operations.py,sha256=pb5CqJ0Th6fCjTNMCtqQMiwH3KezTxAijacglsKUxmY,14730
@@ -13,12 +13,12 @@ pyerualjetwork/model_operations.py,sha256=RKqnh7-MByFosxqme4q4jC1lOndX26O-OVXYV6
 pyerualjetwork/model_operations_cuda.py,sha256=XnKKq54ZLaqCm-NaJ6d8IToACKcKg2Ttq6moowVRRWo,13365
 pyerualjetwork/plan.py,sha256=UzCTFCA9cTv9ITCtsqfJ1g02rCMyescoIV6j1amvYGw,32134
 pyerualjetwork/plan_cuda.py,sha256=hpXZl3h7B1qAVYW-gZebwKMZd4-ftAZ-u05teOJjsno,33525
-pyerualjetwork/planeat.py,sha256=3zCCtrPPs1zxysL73uMdEjYAFcDyJwDtT7y6Jvu4iLk,38872
-pyerualjetwork/planeat_cuda.py,sha256=3y-fC79rRdPa27HwzxUzlBN8y9j--1DezOv7SowVvgM,38865
+pyerualjetwork/planeat.py,sha256=7mWEXHZouy_SfwAnHR2vl3SdHhz4sFnELOGCFhVDm8M,39765
+pyerualjetwork/planeat_cuda.py,sha256=bONKAMZigjuNDZc4mIPxwb9QHZ2oazWE9YS3KxE_JZA,39815
 pyerualjetwork/ui.py,sha256=wu2BhU1k-w3Kcho5Jtq4SEKe68ftaUeRGneUOSCVDjU,575
 pyerualjetwork/visualizations.py,sha256=1SKMZaJ80OD2qHUyMxW1IOv8zwmxzMPxclfbeq1Xr4g,28772
 pyerualjetwork/visualizations_cuda.py,sha256=KbMhfsLlxujy_i3QrwCf734Q-k6d7Zn_7CEbm3gzK9w,29186
-pyerualjetwork-4.2.7b0.dist-info/METADATA,sha256=dICXjXgUm_nrIuFQk45yD0x4JbFfokscOM17gN0_y30,7454
-pyerualjetwork-4.2.7b0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-pyerualjetwork-4.2.7b0.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
-pyerualjetwork-4.2.7b0.dist-info/RECORD,,
+pyerualjetwork-4.2.7b2.dist-info/METADATA,sha256=3-7MhsbqNwShG37tZ-6Ye45krXF_UW1qWcjWubss-Ig,7454
+pyerualjetwork-4.2.7b2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+pyerualjetwork-4.2.7b2.dist-info/top_level.txt,sha256=BRyt62U_r3ZmJpj-wXNOoA345Bzamrj6RbaWsyW4tRg,15
+pyerualjetwork-4.2.7b2.dist-info/RECORD,,