Brest State Technical University, Course "Contemporary Intelligent Information Technology (CIIT)"

From Students' Works (2013)




  • Dog searches for a sausage in the world with wall: evolution & final route of the luckiest dog ... By Lutich Pavel

  • If the field is T-like in which sausage is center of the left end of the top regeon

    (Left) The trace of the luckiest dog after (...) generation ... By Leonchuk Ksenia
    (Right) Also unlucky dog at the 1st generation and so-so-lucky dog during an evolution are shown ... By Vladimir Romanyuk
  • A dog starts at the left end of the bottom of our gridworld looking for a sausage at the right end of the bottom. In between the dog and sausage we have a dengerous cliff at the bottom. If the dog falls down to the cliff dog will die.

    The luckiest dog found in the last generation ... By Galina-Bezabrazova
  • Now dog has a brain with a neural network
  • Let a dog with a 3-3-2 neural network make a navigation in a gridworld avoinding a pond

    (Left) (i) Unlucky dog and (ii) not-so-but-still unlucky dog example ... By LIsenkov Roman
    (Left) An example of lucky dog ... By Lohnitskiy Alexey
    (Right) Another example of lucky dog in a different geography ... By Alexander Mokin
  • Now dog has two senser for smells in addition to the visual sensors. Then a T-maze again but there is a wall as an obstacle between the starting point and sausage. Also old sausage is put at the left end of the top region.

    A successful example ... By Gordievich Ariadna

  • Another example but fresh sausage was mistakenly put at the right end of the top region while old one was put at the left end ... By Galina Bezabrazova



    => Interestingly, one of her dogs is smart enough to find a fresh sausage at the first try before an evolution.


  • A set of 100 points in 2-D space: from random to evolve to be a minimum distance matrix ... By Demchuk Kristina