deletions | additions       diff --git a/sectionIntroduction_.tex b/sectionIntroduction_.tex  index 76ecb45..fa8ab44 100644  --- a/sectionIntroduction_.tex  +++ b/sectionIntroduction_.tex 
...
The key reason abstract concepts such as "dog" can not be generated using the above method is that that there are multiple features in multiple locations that may fire the "dog" neuron. In real life however dog images do not occur with dogs all over the sky and big gigantic ears that exist by themselves without an attached body. Since intuitively, shallower neurons correspond to smaller features and the higher level neurons correspond to combinations of shallower features, a natural approach to fix the issue of generating unrealistic images would be to gather statistics of joint distributions of shallower features. We could use these statistics in a variety of ways. We could for example, use the optimization method mentioned in class and then look at the activations that the optimization method generates. If the activations of the shallow features seem to be an outlier of the joint distribution , we can decide that we need to reduce the activations of certain neurons. Once those neurons have been decided, we can back propagate from any one of those unneeded neurons, and instead take gradients steps to decrease the activation rather than increase it. This could be seen as a method combining both Deconv and and the method introduced by Simonyan.   One could also conceptually have joint distributions of layer k and layer k+1 for all k less than the number of layers. Now suppose we want to generate the abstract concept that a neuron N represents. Initially, we could find which activations of neurons in thelayer  previousto the  layer of are associated with  N happen when N fires high. firing.  Thisof course is  most likely follows  sometype of  distribution. Thus we can sample A the activations  from the joint  distribution and let where we fix  the activations activation  of the previous layer be A. N.  Now we can use the this  same method over and over again  and proceed backwards back  into the image. image where each time we fix in the joint distribution the activations of layer k+1, and sample the marginal for layer k.  As one can see many potential ideas seem plausible with the extra information of statistics generated from many images going through the convnet. We aim to try a few methods, improve our understanding, and then iterate to think of better improved  methods that might generate better images. \section{Problem Statement}