ibrahim5253

#include <iostream>
#include <vector>

namespace std {

template<class T>
class vector<T&> {
public:
    vector() : data(new T*[capacity]) {}

ibrahim5253

#include <memory>

template<class T>
struct node {
    T val;
    node *left;
    node *right;

    node() : left(nullptr), right(nullptr) {}
    node(T v) : val(v), left(nullptr), right(nullptr) {}

ibrahim5253

Dataset	Number of vertices	Number of Edges	Clustering	Lower bound	Upper Bound
AS-733	6474	13895	greedy	7	14
Amazon	262111	1234877	multilevel	19
Karate Club	34	78	multilevel	3	3
Word Adjecency	111		multilevel	3	6

ibrahim5253

Improving VAE by generative adverserial training

Objective

VAEs and GANs are among the few generative models, that have attracted a lot of attention in the past few years. A VAE is good at reconstruction but suffers from blurry images that are the immediate result of pixel-wise MSE in its cost function that imposes an implicit guassian prior. A GAN, on the other hand, replaces this pixel-wise similarity with representations that are learned by its discriminator which is an adversary for the generator. Because of the complex features learned by the discriminator, the generations are quite sharp, but since there is practically no way to know what the discriminator is learning, the generated images may be far from that in the real world. Generator only tries to match the representation of its generation (as seen by the discriminator) with that of the real images.

Keeping in view, the rather complementary features of VAEs and GANs, there have been several attempts at combining these two models to get th

ibrahim5253

{
  1 : 
    {
      gradInput : FloatTensor - empty
      modules : 
        {
          1 : 
            {
              weight : FloatTensor - size: 8192x100
              _type : "torch.FloatTensor"