Basic Examples (3) 

Run an evolution for 3 steps starting from the null k=3, r=1 rule and return every step in the search:

In[1]:=

Out[1]=

Return only the final state of the evolution:

In[2]:=

Out[2]=

Return the final best rule of the evolution:

In[3]:=

Out[3]=

Scope (7) 

Evolve for 500 steps and plot the breakthrough mutation steps:

In[4]:=

Out[4]=

Plot the progressive fitness values showing the mutations that weren't selected:

In[5]:=

Out[5]=

Plot the progressive fitness values for 10 evolutions:

In[6]:=

Out[6]=

Plot the final states of 10 different evolutions:

In[7]:=

Out[7]=

Evolve a k = 4 cellular automata:

In[8]:=

Out[8]=

Evolve for longer automata using "MaxSteps":

In[9]:=

Out[9]=

Evolve to a specific target lifetime:

In[10]:=

Out[10]=

10 separate evolutions to a target lifetime of 50:

In[11]:=

Out[11]=

See the fitness progressions:

In[12]:=

Out[12]=

Evolve the initial conditions of a cellular automata:

In[13]:=

Out[13]=

The default selection function accepts neutral mutations by default, make it so that it accepts mutations that decrease fitness by 1:

In[14]:=

Out[14]=

Use a fitness function that looks for repeating automata rather than terminating ones:

In[15]:=

Out[15]=

Use a fitness function that selects automata with more and more colored cells:

In[16]:=

Out[16]=

Write a mutation function that has a higher probability flipping a rule to white or blue:

In[17]:=

Out[17]=

You can also use index values for the sequence specification:

In[18]:=

Out[18]=

A list of indices will return a list with the result at each respective state:

In[19]:=

Out[19]=

You can also use a span specification, here is the result every 100 steps:

In[20]:=

Out[20]=

Combining this with a list of property specifications will return a list of associations with keys and values for the given specifications:

In[21]:=

Out[21]=

You can generate fitness progressions in a memory-efficient way using "Index":

In[22]:=

Out[22]=

You can also track the mutation distance of the current rule from the initial rule over time:

In[23]:=

Out[23]=

The evolution specification "RuleChanges" will return only the iterations in the evolution where the rule changed:

In[24]:=

Out[24]=

Options (6) 

Use a custom plot sizing function:

In[25]:=

Out[25]=

When "Plot" is specified AdaptiveCellularAutomaton will use any ArrayPlot options given:

In[26]:=

Out[26]=

Plot with a specified region:

In[27]:=

Out[27]=

Specify the width and height of the region:

In[28]:=

Out[28]=

The adaptive search will terminate when the criterion for "WhileCondition" is no longer true:

In[29]:=

Out[29]=

This enables more efficient parallel searches:

In[30]:=

Out[30]=

Neat Examples (1) 

Argument specifications for evolving 2D totalistic cellular automata:

In[31]:=

Out[31]=