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). 
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...

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?

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. :) 
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.

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. 
Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Quote:
there are several questions related to finding the break point of a given hypothesis restriction. So I'm wondering: is there a procedural method that we can follow to find the break points? It is fine using imagination and permutation in one,two or even three dimensional space. But as the dimension increases (often with increasing break point), it seems to be harder and harder to go through each permutation of classification and determine if a given set of points can be shattered. Or did i miss something in the lecture? 
Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Quote:

Re: ddimensional Perceptrons and break points (related to Q4 of homework)
Thanks for intervening Professor.
The 4point set I have in mind is the set of 4 corners of a square. The concept of "shattering" I am working under corresponds to being able to propose a hypothesis that conforms to the classification given for each of the points in the dataset. So in the case of a 2d perceptron, It is easy to "shatter" (if my def. of shattering is correct) the 4 corners in a square if 2 of the corners in one side of the square are red and the other 2 corners are blue  just pass a line in the middle of the square such that the two red points are on one side of the line and the other 2 are on the opposite side. Got your colors inverted? No problem, just multiply the w vector by 1. Now if the red points are on opposite corners (and the blue as well), then we couldn't shatter them because no matter what boundary line we choose, we always get either both sides with the same color or two colors on each side. That's how I understand that the break point for the 2d perceptron is 4 because there exists a 4point set that is not shatterable. Obviously there is a mistake in my concepts somewhere because if you choose a 3 point set in which all points are collinear and you set the middle point to blue and the outer points to red, this is not shatterable by a 2d perceptron, or a 3d perceptron or any higher dimensional perceptron. I hope I made clear what my doubts are and where is my confusion. 
All times are GMT 7. The time now is 03:06 AM. 
Powered by vBulletin® Version 3.8.3
Copyright ©2000  2021, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. AbuMostafa, Malik MagdonIsmail, and HsuanTien Lin, and participants in the Learning From Data MOOC by Yaser S. AbuMostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.