# Tag Info

7

The Focus of This Question "How can ... we process the data from the true distribution and the data from the generative model in the same iteration? Analyzing the Foundational Publication In the referenced page, Understanding Generative Adversarial Networks (2017), doctoral candidate Daniel Sieta correctly references Generative Adversarial Networks, ...

6

If you start with perpect discriminator, loss function will be saturated, and gradient of loss will be very small, so feedback for the generator also will be small, and learning will be slow down as a result. Actually, it is allways desired for discriminator and generator to learn balancedly. Additionally, it is claimed that Wasserstein Loss take care of ...

5

Latent is a synonym for hidden. Why is it called a hidden (or latent) variable? For example, suppose that you observe the behaviour of a person or animal. You can only observe the behaviour. You cannot observe the internal state (e.g. the mood) of this person or animal. The mood is a hidden variable because it cannot be observed directly (but only ...

5

It is called a Latent variable because you cannot access it during train time (which means manipulate it), In a normal Feed Forward NN you cannot manipulate the values output by hidden layers. Similarly the case here. The term originally came from RBM's (they used term hidden variables). The interpretation of hidden variables in the context of RBM was that ...

5

To understand this equation first you need to understand the context in which it is first introduced. We have two neural networks (i.e. $D$ and $G$) that are playing a minimax game. This means that they have competing goals. Let's look at each one separately: Generator Before we start, you should note that throughout the whole paper the notion of the data-...

4

Compare generated and real data All the results produced by G are always considered "wrong" by definition, even for a very good generator. You provide the discriminative neural network $D$ with a mix of results generated by the generator network $G$ and real results from an outside source, and then you train it to distinguish if the result was produced by ...

4

Not necessarily it depends on the function of the problem space for both the GANs. A real world example: a batter's reaction time and a pitchers max speed are actual bounded values based on genetics and physics. If the max speed a pitcher can pitch is greater than the max reaction time a human needs to effectively hit against them they will permanently be ...

4

In fact, autoencoders are used for generative tasks. Have a look at Tutorial on Variational Autoencoders (VAEs). The coolest thing about VAE is that abstract features can be easily amplified or suppressed based on extracted vectors from the latent space. Let's imagine a model trained on MNIST to generate digits. If you take two images of the same digit which ...

4

Auto-encoders are widely used and maybe even more used than GANs (in fact, auto-encoders are older than GANs, although the main general idea behind GANs is quite old). For example, auto-encoders are used in World Models, for drug design (e.g. see this paper) and many other tasks that involve data compression or generation. So, if we train autoencoders, for ...

4

I guess the issue is you lost track of where the samples came from and since you requested a math explanation I'll try to go step by step using my notation and without checking other material to avoid being biased by how other authors present it So we start from $$L(D,G) = E_{x \sim p_{r}(x)} \log(D(x)) + E_{x \sim p_{g}(x)}\log(1 - D(x))$$ then you apply ...

3

We can already observe information bubbles on social media, where the circle is that the ML algorithms learn what content people like and give more similar content based on clicks and so on. From a single wrong click, you could enter a bubble and never come out if you don't take care or be aware. This happens with humans, so the same may apply to computers. ...

3

I think you'll enjoy this work from Apple on improving the realism of synthetic images. Essentially what you need to do is generate a synthetic image then have your GAN modify the synthetic image so that a 1) a discriminator thinks it is real while also 2) not changing the gross structure of the image very much (so the traffic sign doesn't move) - yes, this ...

3

The key is: VAE usually use a small latent dimension, the information of input is so hard to pass through this bottleneck, meanwhile it tries to minimize the loss with the batch of input data, you should know the result -- VAE can only have a mean and blurry output. If you increase the bandwidth of the bottleneck, i.e. the size of latent vector, VAE can get ...

3

In essence, Variational Autoencoders learn an "explicit" distribution of the data by trying to fit the data via a multi-dimensional Gaussian/Normal distribution. However, Generative Adversarial Networks learn an "implicit" distribution of data meaning that you cannot directly sample them. Also, due to the deterministic nature of neural networks GANs tend to ...

3

With Generative Adversarial Networks, all the generator cares about is fooling the discriminator. There's no requirement to be clever, or exhaustive, or make efficient use of the input space. As long as the discriminator returns "real" (vs. "fake") the generator "wins". The hope is that as the generator and discriminator are trained simultaneously, each ...

3

The paper StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks should provide the answers to your questions. Here's an excerpt from the abstract of the paper. Synthesizing photo-realistic images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated ...

3

What's the input to the Generator? In the basic implementation of GANs, the Generator only takes in a vector of random variables. This might seem strange, but after training, the generator can transform this input noise into an image resembling those of the training set. How does it work? It is trained along with its counterpart the Discriminator, whose goal ...

3

In reality GANs are not made for image classification, but for data generation, and they have gained popularity on image generation. They are also used for tabular data generation, see for example TGAN, or for time series generation, e.g. Quant GAN. You have even some application for the field of graphs and networking, e.g. NetGAN and GraphGAN.

3

It seems your question is concerned with how an empirical mean works. It is indeed true that, if all $x^{(i)}$ are independent identically distributed realisations of a random variable $X$, then $\lim_{n \rightarrow \infty} \frac{1}{n}\sum_{i=1}^n f(x^{(i)}) = \mathbb{E}[f(X)]$. This is a standard result in statistics known as the law of large numbers.

3

Sorry cannot directly reply to your comment as I posted without an account, and you were right! I replaced transposed layers with Upscale1D+Conv1D and that solved the issue. gen = Conv1DTranspose(128, 4, strides=2, padding='same', kernel_initializer=w_init, use_bias=None)(gen) should become (notice that strides=2 becomes strides=1): gen = Upscale1D()(gen) ...

2

A discriminative network ($D$) learns to discriminate by definition - we provide it with the true and the generated data, and let it learn by itself how to discriminate between the two. Therefore, we expect network $D$ to improve the ability of network $G$ to generate better and better images (or other kind of data), as it try to "trick" network $D$ by ...

2

Let's start at the beginning. GANs are models that can learn to create data that is similar to the data that we give them. When training a generative model other than a GAN, the easiest loss function to come up with is probably the Mean Squared Error (MSE). Kindly allow me to give you an example (Trickot L 2017): Now suppose you want to generate cats ; you ...

2

2

The problem isn't the GAN but the implementation of its discriminator which is typically a convolutional neural network (CNN). CNNs have trouble with sparse data. They require dense data to learn well. There are ways to work around this. See the following for some ideas: Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation Sparse ...

2

GANs were invented in a bar somewhere in Montreal, Canada. At said bar, the idea was that neural networks could be used for generating new examples from an existing distribution. This was the problem: Given an input set $X$, can we make a new $x'$ that looks like it should be in $X$? The classic description of a GAN is a counterfeiter (generator) and a cop ...

2

In my experience, GANs work really well for the scenario of semi-supervised learning, where you don't necessarily have labels for all your class $B$ data, but you do have a balanced dataset. In my (limited) experience, you do have to have a balanced (in numbers) set of $A$ and $B$ objects, even though you are not sure of the labels. And yes, GANs can overfit ...

2

It looks like you're asking about the difference between using conditional and joint probabilities. The joint probability $$D(x,y)$$ is the probability of x and y both happening together. The conditional probability $$D(x | y)$$ is the probability that x happens, given that y has already happened. So, $$D(x,y) = D(y) * D(x | y)$$. Notice that, in a C-GAN,...

2

"Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines.". Source: "Attacking Machine Learning with Adversarial Examples" You create an input and test against the output, tuning the input to maximize the error. There are ...

2

The main reason that the discriminator is trained concurrently with the generator is to provide (at least in theory) a smooth and gradual learning signal for the generator. If we trained the discriminator on only the input data, then, assuming our training algorithm converges well, it should quickly converge to a fixed model. The generator can then learn to ...

2

I'll answer your questions one by one: In this equation are the $E_{z \sim p_z(z)}$ and $E_{x \sim p_{data}(x)}$ the means of the distributions of the mini batch samples? So let's take the first part $E_{x \sim p_{data}(x)}[log \,D(x)]$. This is read as the "expected value of $log \, D(x)$, where $x$ is sampled from $p_{data}(x)$". So, in simpler terms ...

Only top voted, non community-wiki answers of a minimum length are eligible