1

there are two simple neural model with three neurons as in the picture. The only learning parameter in each neuron is a threshold of theta. Each neuron provide an output of $+1$ if summation of inputs gets bigger than the neuron's threshold unless the output will be $-1$.

$1$- What are the VC-Dimension on these models.

enter image description here

$2$-If an animal after $n=40$ round training can recognize "far", "close but safe" and "close and unsafe" situation with $20$% accuracy. And if we are $95$% sure about aforementioned statement. Which of these two models are better suggestion to model this cognitive behavior of the animal.

Zia
  • 439
Judy Abbot
  • 11
  • What is $x$, one-dimensional? I would read your description that everything in model A is one-dimensional, so that the output really only depends on the first threshold and its yes-no-decision. Which would rule it out for the second task that requires three responses. – Lutz Lehmann Feb 13 '14 at 09:41

0 Answers0