
#1




ddimensional Perceptrons and break points (related to Q4 of homework)
Hello:
In slide 9 of lecture 5 (minute 33:03), the Professor gives an example of 3 colinear points for which there can be no possible hypothesis. Still, "it doesn't bother us because we want the maximum bound of possible dichotomies", so k=3 is not considered as a breakpoint. My question is: In a ddimensional perceptron, it appears we would not consider a set of points lying in a (d1)dimensional hyperplane as candidates for giving an "impossible" dichotomy. Why? Is it because the probability of picking such a set of points from the input space that all lie in a (d1) dimensional space is zero? (As in the case of picking 3 collinear points in a plane). 
#2




Re: ddimensional Perceptrons and break points (related to Q4 of homework)
No, the probability isn't cero. The question is that we are interested in the maximum of points our hypothesis can shatter. So you must take a set of points that maximizes the probability of shatter the most...

#3




Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Quote:
It turns out that the power of the hypothesis set comprising perceptrons increases as the dimension of their domain increases. The three points are a good example. If colinear, they cannot be shattered, regardless of what dimension space they are in. If not colinear, they can always be shattered: this requires the domain to be at least dimensional. 
#4




Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Ok. This 3 point set: +1 1 +1 cannot be shattered if the 3 points are collinear, no matter what dimension the perceptron is. Why isnt three the break point for a 2d perceptron (or a 3d perceptron, for that matter)? What is the reason that we must consider point sets that are in the same dimension as the input space?

#5




Re: ddimensional Perceptrons and break points (related to Q4 of homework)
That's simply a matter of the definition!
The break point is the (minimum) value of such that no set of points can be shattered. To put it another way, it is the (minimum) value of such that every set of points fails to be shattered. Finding one set of points that fails to be shattered is consistent with the existence of a break point, but you need to demonstrate all other sets of points have the same property. 
#6




Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Now I'm confused. The break point for 2d perceptrons is 4. In lecture 5, one example of a 4point set is given that is not shatterable. However, there are other 4point sets that are (shatterable). Likewise for positive rays, positive intervals, where the break point is 2 and 3 respectively.

#7




Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Quote:
It is actually not possible to shatter any set of 4 points using the 2dimensional perceptron. Perhaps we can discuss the set of points you have in mind and look for which dichotomies would be impossible there.
__________________
Where everyone thinks alike, no one thinks very much 
Tags 
break points, perceptron 
Thread Tools  
Display Modes  

