Here is a snippet from the article.
A player’s move was determined by evaluating the presumed quality of the resulting future positions. The evaluation function was structured as an artificial neural network comprising an input layer, three internal processing (hidden) layers, and an output node (Figure 2). The first internal processing layer was designed to indicate the spatial characteristics of the checkerboard without indicating explicitly how such knowledge might be applied. The remaining internal and output neurons operated based on the dot product of the evolvable weighted connections between nodes and the activation strength that was emitted by each preceding node. Each node used a hyperbolic tangent (tanh, bounded by ±1) with an evolvable bias term. In addition, the sum of all entries in the input vector was supplied directly to the output node, constituting a measure of the relative piece differential.
Notice the words "structured" and "designed". The programmers set value to moves that produced positive results so that the programs evolution function could examine the possible moves and learn from the past what has provided the most favorable outcome.
What would be a real miracle here was if the program "evolved" to be a master chess player. It is however constrained to be an expert checkers player. It cannot evolve past that and was "designed" by designers to learn to become as such. This is not a program that "sprang out of existence" or evolved to do something new. It was given variables and assigned values to assess positives with a goal of achieving the highest possible outcome. But it could not be possible without the designers and further will not evolve into anything besides an expert checkers player.
Even the article when they describe being called out by human players for relying on a program the designers themselves say it was more the program relying on them!
A player’s move was determined by evaluating the presumed quality of the resulting future positions. The evaluation function was structured as an artificial neural network comprising an input layer, three internal processing (hidden) layers, and an output node (Figure 2). The first internal processing layer was designed to indicate the spatial characteristics of the checkerboard without indicating explicitly how such knowledge might be applied. The remaining internal and output neurons operated based on the dot product of the evolvable weighted connections between nodes and the activation strength that was emitted by each preceding node. Each node used a hyperbolic tangent (tanh, bounded by ±1) with an evolvable bias term. In addition, the sum of all entries in the input vector was supplied directly to the output node, constituting a measure of the relative piece differential.
Notice the words "structured" and "designed". The programmers set value to moves that produced positive results so that the programs evolution function could examine the possible moves and learn from the past what has provided the most favorable outcome.
What would be a real miracle here was if the program "evolved" to be a master chess player. It is however constrained to be an expert checkers player. It cannot evolve past that and was "designed" by designers to learn to become as such. This is not a program that "sprang out of existence" or evolved to do something new. It was given variables and assigned values to assess positives with a goal of achieving the highest possible outcome. But it could not be possible without the designers and further will not evolve into anything besides an expert checkers player.
Even the article when they describe being called out by human players for relying on a program the designers themselves say it was more the program relying on them!
We are not made happy by what we acquire but by what we appreciate.
