#67: Hypn(0)tism

 

Rosenblatt describes multiple algorithms for training this model

“reinforcement systems”

 

that are clearly influenced by Hebb’s theory of learning in real neural networks. Some algorithms that only strengthen the connections between activated

S-Units

“positive reinforcement”

 

and

A-Units

 

some that only weaken the connection between activate

 

S-Units

 

“negative reinforcement”

 

 

and some that use a combination of both. Interestingly, Rosenblatt is able to prove that these algorithms will always (eventually) yield a solution, if such a solution exists. Later Minsky and Papert found in their paper “Perceptrons: an introduction to computational geometry.” that such solutions only exist for linearly separable problems.

 

Their famous counterexample was

 

The XOR-problem

 

that can’t be solved using the perceptron as imagined by Rosenblatt.

Reklamy

Zanechat odpověď

Vyplňte detaily níže nebo klikněte na ikonu pro přihlášení:

Logo WordPress.com

Komentujete pomocí vašeho WordPress.com účtu. Odhlásit /  Změnit )

Google+ photo

Komentujete pomocí vašeho Google+ účtu. Odhlásit /  Změnit )

Twitter picture

Komentujete pomocí vašeho Twitter účtu. Odhlásit /  Změnit )

Facebook photo

Komentujete pomocí vašeho Facebook účtu. Odhlásit /  Změnit )

Připojování k %s