10
votes
Accepted
Is the new AlphaGo implementation using Generative Adversarial Networks?
No, GANs are not used. It's reinforcement learning at what it does best. The tree search is an interesting addition and assists with navigating the sheer scale of the game.
Although the agent was ...
- 3,707
9
votes
Accepted
What is the meaning of $V(D,G)$ in the GAN objective function?
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 ...
- 3,153
8
votes
Accepted
Can someone explain R1 regularization function in simple terms?
Here is how I understand this regularization.
$R_1$ is simply the norm of the gradients, which indicates how fast the weights will be updated. Gradient regularization penalizes large changes in the ...
- 847
7
votes
Why doesn't VAE suffer mode collapse?
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 ...
- 288
7
votes
Accepted
How can we process the data from both the true distribution and the generator?
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 ...
- 7,385
7
votes
Can I start with perfect discriminator in GAN?
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 ...
- 194
6
votes
Why don't OpenAI train a deep learning model to identify correct and incorrect information in ChatGPT's responses?
You are massively underestimating the difficulty of the task, you would need:
A dataset containing labels of correct/incorrect, at a similar scale (billions of data points).
A definition of correct/...
- 1,112
5
votes
Why is it called Latent Vector?
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 ...
- 37.1k
5
votes
Accepted
Isn't deep fake detection bound to fail?
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 ...
- 545
5
votes
What are the fundamental differences between VAE and GAN for image generation?
GANs generally produce better photo-realistic images but can be difficult to work with. Conversely, VAEs are easier to train but don’t usually give the best results.
I recommend picking VAEs if you ...
- 1,698
4
votes
How are generative adversarial networks trained?
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 ...
- 873
4
votes
Why is the variational auto-encoder's output blurred, while GANs output is crisp and has sharp edges?
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 ...
- 49
4
votes
Are deep learning models suitable for training with sparse data?
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 ...
- 1,698
4
votes
Accepted
Why is the Jensen-Shannon divergence preferred over the KL divergence in measuring the performance of a generative network?
Lets start with question 1) how does JS-divergence handles zeros?
by definition:
\begin{align}
D_{JS}(p||q) &= \frac{1}{2}[D_{KL}(p||\frac{p+q}{2}) + D_{KL}(q||\frac{p+q}{2})] \\
&= \frac{...
- 2,339
4
votes
Accepted
Why is the mean used to compute the expectation in the GAN loss?
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 $\...
- 4,420
4
votes
Why don't we use auto-encoders instead of GANs?
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 ...
4
votes
Accepted
Why don't we use auto-encoders instead of GANs?
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 ...
- 37.1k
4
votes
Accepted
Where is the mistake in my derivation of the GAN loss function?
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 ...
- 799
4
votes
GAN Generator Output w/ Periodic Noise
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.
...
- 31
4
votes
What is Lipschitz constraint and why it is enforced on discriminator?
The Lipschitz constraint is essentially that a function must have a maximum gradient. The specific maximum gradient is a hyperparameter.
It's not mandatory for a discriminator to obey a Lipschitz ...
- 678
4
votes
Accepted
Why are GAN models not heavily used for NLP?
A couple of reasons:
Transformers are amazing at text generation already (e.g. GPT-3 which almost passes the Turing-Test)
The original GAN requires a continuous data representation (e.g. images) ...
- 306
4
votes
Accepted
Why doesn't the inception score measure intra-class diversity
For reference, a recap of Inception Score:
The inception score is computed by comparing the categorical output distributions of an inception model, given examples from real vs synthetic images. If the ...
- 1,327
3
votes
Why do we need Upsampling and Downsampling in Progressive Growing of Gans
Use of Transposed Convolution can lead to checkerboard artifacts. So we prefer to up-sample and then apply convolution. You can check this article for more information https://distill.pub/2016/deconv-...
3
votes
Accepted
Using GAN's to generate dataset for CNN training
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 ...
- 327
3
votes
Accepted
What is the purpose of the GAN?
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:
...
- 3,707
3
votes
How can we process the data from both the true distribution and the generator?
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 ...
- 1,176
3
votes
Accepted
What kind of algorithm is used by StackGAN to generate realistic images from text?
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.
...
3
votes
Accepted
How does the generator in GAN's work?
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 ...
- 3,153
3
votes
Have GANs been used to solve regression problems?
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 ...
- 381
Only top scored, non community-wiki answers of a minimum length are eligible