Transcriptions
Note: this content has been automatically generated.
00:00:00
i one mechanism and today i'm going to talk about are using a neural network to guide expression transformation
00:00:07
so imagine you are given some kind of objects such as religious cubes on which can apply transformations
00:00:12
and you are interested in finding pass so sequence of
00:00:16
transformations which can go from one configuration to another
00:00:20
if you blindly do that during to a problem is that the problem is that there
00:00:25
are so many states and it's impossible to get him visit them all blindly
00:00:30
so what i do in my work is that i use a neural network to guide the search and the idea is very simple so
00:00:36
you take two objects you feed them to the network and used output
00:00:41
an estimation of the number of transformation that must be applied
00:00:44
in order to reach the targets and uses information we can devise not go isn't that we'll really approaches solution
00:00:53
now in my work i'm not using rubik's cubes at my objects but mathematical expressions
00:00:59
and they look something like this so your valuables addition
00:01:03
and multiplication in addition it's expressions of focus
00:01:07
which is where we can apply transformations the transformations we consider our
00:01:13
commute activity as a city city and you should be t. v. t. v. and
00:01:17
also operations which moves focus on the expression to modify different part of expression
00:01:25
oh this is an overview of the system and it's very simple what we do is we take do expressions with a focus
00:01:32
we feed them to us realistically um and requesting on network and whipped in points in a
00:01:37
very high dimensional space and then we simply measures it the distance between those two points
00:01:45
so we twenties network fun fun fun six million barrels of examples of expressions
00:01:51
uh with distances ranging from one to ten and at the end
00:01:55
we obtain it system that is able to approximate the
00:01:59
the distance between expressions within minutes rudolph less than one
00:02:05
so here we see the performance of a whole system that compared to breadth first search
00:02:10
and we can see that our system is able to find parts between expressions um
00:02:17
in both cases in less than one second compared to um the efforts in two minutes
00:02:25
so this project is available online uh and get up at this address and was
00:02:30
built using tightened by george so thank you very much for your attention