1. Re: Neural networks -Reply
Random combination of the "fittest" organisms in an environment - where
fitness is a function of interaction with the environment *does* produce
superior organisms, at least in the problem domain. Natural selection
does work, but mere random shuffling of genes without a
meta-environment evaluation function will not.
-Jay Turley
>>> MilesDaniel <handmade at CITILINK.COM> 02/18/99 09:37pm >>>
You do not say, but seem to suggest, that there is in life a law of
evolution that allows random combinations to produce superior
organisms. I
do not see this program as proof of that. The variables that are
minipulated in this program are obviously geared toward success.
Random is
random. It leads to nothing more than randomness. A true scientist would
tell you that there is no proof for evolution. There has never been
transitional forms of species found. A true scientist would tell you that
is takes more faith to believe in evolution that to believe we were created
by God.
We were, you know!
I compliment you on coding this program. It seems to run good.
Next?
-Somebody-
At 06:38 PM 2/18/99 -0500, you wrote:
>Here is a simple natural selection program I made last week.
>It's a text based display.
>It shows the evolution of a group of organisms.
>The organisms each have a string of dna. when 2 organisms reproduce
>random pieces are selected from each parent to form the dna for the
>offspring. dna values of {0,0} will produce weak statistics,
>values of {1,0} or {0,1} will produce moderate statistics,
>and {1,1} will produce high statistics. At birth the dna is used to
>calculate the organisms beginning health and it's natural ability to
>collect food. Each day the organisms will collect food from the food
>source, which accumulates each day. The higher their ability to collect
>food, the more food they will collect. If an organism doesn't collect
>enough food to feed itself it will loose health. If there is not enough
>food in the food source for all organisms, then the organisms will limit
>how much food they will collect so that the colony has a better chance
to
>survive. organisms can only reproduce with organisms of the same
>generation. There can only be 3 generations alive at one time. this is to
>prevent over population.
>Organisms highlighted purple have just mated.
>Organisms highlighted red are dead.
>Organisms highlighted green means that it's the last surviving of it's
>generation and will lose 1 health per day due to old age, to make way
for
>new generations.
>
>reproducing requires that both parents be above a certain age and
uses
>up some of the parents food. reproducing also causes the loss of some
>health. The age and food requirement becomes higher as the
generations
>increase.
>
>You will notice that even though the offspring are produced by random
>combinations of their parents, higher generations will be born with
>superrior stats than the begining organisms.
>
>I hope I didn't miss anything out. If you have any comments or questions
>just e-mail me.
>
>---------------------------------------------------------
>--Begin Code
>--Dna.e
>--Liquid-Nitrogen Software 1999
>---------------------------------------------------------
>
>include graphics.e
>include machine.e
>
>object junk
>
>tick_rate(100)
>integer ROWS
>if text_rows(50) != 50 then
> puts(1,"Couldn't set 50 text rows, must use 25.\nPress any key.")
> while get_key() != -1 do end while
> while get_key() = -1 do end while
> ROWS = 20
>else
> ROWS = 45
>end if
>cursor(NO_CURSOR)
>
>integer max_age, number_dead, food, food_growth, days, dpy, als,
total_org_days, max_gen, min_gen
>sequence max_age_tag
>max_age = 0
>max_age_tag = " "
>number_dead = 0
>food = 2000
>food_growth = 20
>days = 0 --days passed since start.
>dpy = -1 --deaths per year
>als = 0 --average lifespan
>total_org_days = 0 --combined days lived total
>max_gen = 1
>min_gen = -1
>
>sequence orgs, reproduced, old
>
>orgs = {}
>reproduced = {}
>old = {}
>
>--dna = {health,health,health,health, fcol,fcol,fcol}
>-- (1) (2) (3) (4) (5) (6) (7)
>--org = {age, health, food, food_collect, dna, tag, generation}
>
>--current dna structure:
> -- 001..020 health
> -- 021..060 food collection
>
>constant vowels = "AEIOU"
>function create_org(sequence dna, integer g)
>sequence org
> g += 1
> org = {0,0,90 + (g*10),0,dna, rand({26,26,26,26})+'@', g}
> if g > max_gen then
> max_gen = g
> min_gen = g-2
> end if
> org[6][rand(4)] = vowels[rand(5)]
> for i = 1 to 20 do
> if compare(dna[i],{0,0})=0 then
> org[2] += 5
> elsif compare(dna[i],{1,1})=0 then
> org[2] += 20
> else
> org[2] += 10
> end if
> end for
> for i = 21 to 60 do
> if compare(dna[i],{0,0})=0 then
> org[4] += 0
> elsif compare(dna[i],{1,1})=0 then
> org[4] += 2
> else
> org[4] += 1
> end if
> end for
> if org[4] = 0 then
> org[4] = 1
> end if
> return org
>end function
>
>function mix_dna(sequence g1, sequence g2)
>sequence g3
> g3 = g1
> for i = 1 to length(g1) do
> if rand(50) = 1 then
> g3[i][1] = rand(2)-1
> else
> if rand(2) = 1 then
> g3[i][1] = g1[i][1]
> else
> g3[i][1] = g2[i][1]
> end if
> end if
> if rand(50) = 1 then
> g3[i][2] = rand(2)-1
> else
> if rand(2) = 1 then
> g3[i][2] = g1[i][2]
> else
> g3[i][2] = g2[i][2]
> end if
> end if
> end for
> return g3
>end function
>
>procedure do_day()
>sequence temp, new
>integer food_limit, food_get, eater, rok
> days += 1
> food += rand((food_growth + max_gen)*15)
> if rand(20) = 1 then
> food += rand((food_growth + max_gen)*30)
> elsif rand(30) = 1 then
> food += rand((food_growth + max_gen) * 100)
> end if
> if rand(10) = 1 then
> food_growth += (rand(5)-3)
> if food_growth < 10 then
> food_growth = 10
> elsif food_growth > 30 then
> food_growth = 30
> end if
> end if
>
> temp = {}
> new = {}
> reproduced = {}
> old = {}
> for i = 1 to length(orgs) do
> orgs[i][1] += 1
> if orgs[i][2] > 0 then
> temp = append(temp,orgs[i])
> else
> if orgs[i][1] > max_age then
> max_age = orgs[i][1]
> max_age_tag = orgs[i][6]
> end if
> number_dead += 1
> total_org_days += orgs[i][1]
> food += orgs[i][1]
> food += orgs[i][3]
> end if
> end for
> orgs = temp
>
> if length(orgs) > 0 then
> food_limit = floor(food/length(orgs))+1
> end if
>
> for i = 1 to length(orgs) do
> --collect food
> food_get = rand(orgs[i][4])
> if food_get > food_limit then
> food_get = food_limit
> end if
> if food >= food_get then
> orgs[i][3] += food_get
> food -= food_get
> else
> orgs[i][3] += food
> food = 0
> end if
> --eat food
> eater = 10 + floor(max_gen/4)
> if eater > 60 then
> eater = 60
> end if
> orgs[i][3] -= rand(eater)
> if orgs[i][3] < 0 then
> orgs[i][2] += orgs[i][3]
> if orgs[i][2] < 0 then
> orgs[i][2] = 0
> end if
> if orgs[i][3] < 0 then
> orgs[i][3] = 0
> end if
> end if
> --old_age
> rok = 0
> for x = 1 to length(orgs) do
> if i != x then
> if orgs[x][7] <= orgs[i][7] then
> rok = 1
> end if
> end if
> end for
> if rok = 0 then
> orgs[i][2] -= 1
> old = append(old,orgs[i][6])
> end if
>
> --reproduce
> if orgs[i][2] > 0 and orgs[i][1] > (orgs[i][7]*30)+20 and orgs[i][3] > 45
+ (orgs[i][7]*5) then
> rok = 1
> for x = 1 to length(orgs) do
> if x != i then
> if orgs[x][7] <= min_gen then
> rok = 0
> end if
> end if
> end for
>
> if rok = 1 or orgs[i][7] <= min_gen then
> for x = 1 to length(orgs) do
> if x != i then
> if orgs[i][7] = orgs[x][7] then
> if orgs[x][2] > 0 and orgs[x][1] > (orgs[x][7]*30)+20 and orgs[x][3] >
45 + (orgs[x][7]*5) then
> orgs[i][3] -= 45 + (orgs[i][7]*5)
> orgs[x][3] -= 45 + (orgs[x][7]*5)
> orgs[i][2] -= (rand(10)+10)
> orgs[x][2] -= (rand(10)+10)
> reproduced = append(reproduced, orgs[i][6])
> reproduced = append(reproduced, orgs[x][6])
> new = append(new, create_org(mix_dna(orgs[i][5],orgs[x][5]),
orgs[i][7]))
> exit
> end if
> end if
> end if
> end for
> end if
> if orgs[i][2] < 0 then
> orgs[i][2] = 0
> end if
> if orgs[i][3] < 0 then
> orgs[i][3] = 0
> end if
> end if
> end for
> for i = 1 to length(new) do
> orgs = append(orgs,new[i])
> end for
>
>end procedure
>
>for i = 1 to 15 do
> junk = rand(repeat({2,2},60))-1
> for x = 1 to length(junk) do
> junk[x][1] = junk[x][1] * (junk[x][2] = 0)
> end for
> for x = 1 to 80 do
> junk[rand(60)][rand(2)] = 0
> end for
> --? junk
> orgs = append(orgs, create_org(junk, 0))
>end for
>
>--integer max_age, number_dead, food, food_growth, days
>--sequence max_age_tag
>--org = {age, health, food, food_collect, dna, tag, generation}
>
>integer disp_wait, wait_max
>disp_wait = 1
>wait_max = 1
>
>integer key, max_disp
>atom tim
>key = -1
>while 1 do
> tim = time()
> key = get_key()
>
> if key = 27 and length(orgs) = 0 then
> exit
> end if
> if key = 27 then
> orgs = {}
> end if
>
> do_day()
>
> disp_wait += 1
> if disp_wait > wait_max then
> disp_wait = 1
> position(1,1)
> mem_set(#B8000,0,160)
> text_color(7)
> printf(1,"Days:%6d, Food:%5d, Food-Growth:%3d,
> printf(1,"Most-Days-Lived: %s:%6d, Number-Dead:%5d.
> puts(1,"\n\n")
> --printf(1,"\n%d \n",min_gen)
>
> max_disp = length(orgs)
> if max_disp > ROWS then
> max_disp = ROWS
> end if
>
> --org = {age, health, food, food_value, food_collect, dna, tag,
generation}
> for i = 1 to 47 do
> mem_set(#B8000 + (i+2)*160, 0, 160)
> if i <= max_disp then
> if find(orgs[i][6],reproduced) then
> text_color(5)
> elsif orgs[i][2] = 0 then
> text_color(4)
> elsif find(orgs[i][6],old) then
> text_color(2)
> else
> text_color(7)
> end if
> printf(1,"Gen:%3d Name:%s. Age:%5d. Health:%3d. Food:%5d,
gs[i][4]})
> end if
> end for
> if length(orgs) = 0 then
> puts(1,"All Organisms Have Died.\n")
> if dpy = -1 then
> dpy = floor(number_dead / (days/365))
> if number_dead = 0 then
> als = 0
> else
> als = floor(total_org_days / number_dead)
> end if
> end if
> if dpy > -1 then
> printf(1,"Average-Deaths-Per-Year:%4d.\n",dpy)
> printf(1,"Average-Life-Span:%6d days.\n",als)
> end if
> end if
> end if
>
> --Comment these next 2 lines out so you can see what happens over
a
longer period of time.
> while time() - tim < .3 do --Waiting...
> end while
>end while
>
>------------
>--End Code--
>------------
>
