Questions tagged [generative-model]

For questions related to the concept of generative machine learning models, such as the Restricted Boltzmann Machine (RBM), the Variational Autoencoder (VAE), and the Generative Adversarial Network (GAN).

Filter by
Sorted by
Tagged with
3
votes
0answers
64 views

Creating an AI than can learn to give instructions

So we think a computer is dumb because it can only follow instructions. Therefor I am trying to create an AI that can give instructions. The idea is this: Create a geometric scene (A) then make a ...
3
votes
0answers
126 views

Speaker Identification / Recognition for less size audio files

I am working on speaker identification problem using GMM (Gaussian Mixture Model). I have to just identify one user present in the given audio, so for second class noise or silent audio may use or not ...
2
votes
0answers
17 views

Improving graph decoder network

I have been using a network to generate graphs. The architecture that I have been using is the following: In this figure, $D_1$ is the signal generator and $D_2$ is the graph topology generator, ...
4
votes
1answer
464 views

What is the input for the prior model of VQ-VAE?

I'm trying to implement the VQ-VAE model. In there, a continuous variable $x$ is encoded in an array $z$ of discrete latent variables $z_i$ that are mapped each to an embedding vector $e_i$. These ...
2
votes
1answer
60 views

Giving an AI a purpose to talk

I am trying to teach my AI to talk. The problem is I'm struggling to find a good scenario in which it needs to. Some ideas I had were: "Describe a geometric scene" - Then together with a parser we ...
5
votes
1answer
343 views

Does MMD-VAE solve the problem of blurred images of vanilla VAEs?

I understand that with vanilla VAEs, there are a few reasons justifying the production of blurred out images. The InfoVAE paper describes the case when the decoder is flexible enough to ignore the ...
2
votes
0answers
257 views

Are there any general tips for troubleshooting a VAE when apparently it is not learning?

I am trying to train a VAE for anomaly detection. I chose one architecture from this Github repository and I adjusted the input and output to match what I need. In my case, the input (and hence the ...
5
votes
1answer
195 views

Context-based gap-fill face posture-mapper GAN

These images are handmade, not auto-generated like they will be in production. Apologies for inaccuracies in the graph overlay. I am trying to build an AI like that displayed in the diagram: when ...
3
votes
1answer
83 views

How exactly does adversarial training help in handling mode-collapse in generative networks?

Of my understanding mode-collapse is when there happen to be multiple classes in the dataset and the generative network converges to only one of these classes and generates images only within this ...
1
vote
1answer
94 views

Why does the discriminator minimize the cross-entropy while the generator maximize it?

In his original GAN paper Goodfellow gives a game theoretic perspective for GANs: \begin{equation} \underset{G}{\min}\, \underset{D}{\max}\, V\left(D,G \right) = \mathbb{E}_{x\sim\mathit{p}_{\...
1
vote
0answers
33 views

What's a good generative model for creating valid formats of a person's name?

I'm trying to come up with a generative model that can input a name and output all valid formats of it. For example, "Bob Dylan" could be an input and the gen model will output "Dylan, Bob", "B ...
0
votes
1answer
27 views

How to change this RNN text classification code to become text generation code?

I can do text classification with RNN, in which the last output of RNN (rnn_outputs[-1]) is used to matmul with output layer weight and plus bias. That is getting a word (class name) after the last T ...
3
votes
2answers
62 views

How can we find find the input image which maximizes the class-probability for an ANN?

Let's assume we have an ANN which takes a vector $x\in R^D$, representing an image, and classifies it over two classes. The output is a vector of probabilities $N(x)=(p(x\in C_1), p(x\in C_2))^T$ and ...
3
votes
1answer
349 views

Which approach can I use to generate text based on multiple inputs?

I have a little experience in building various models, but I've never created anything like this, so just wondering if I can be pointed in the right direction. I want to create (in python) a model ...
2
votes
1answer
179 views

What is the purpose of the noise injection in the generator network of a GAN?

I do not understand why with enough training how the generator cannot learn all images from the training set as a mapping from the latent space - It is the absolute optimal case in training as it ...
0
votes
1answer
794 views

Query regarding the minmax loss function formulation of the training of a Generative Adversarial Network (GAN)

Just needed a clarification on the training procedure for a standard GAN. Of my understanding the loss function to optimize is a min max (max min causing mode collapse due to focus on one class ...
0
votes
1answer
71 views

If the goal of training of a GAN is to have $P_g=P_{data}$, shouldn't this produce the exact same images?

Referring to the blog, Image Completion with Deep Learning in TensorFlow, it clearly says that we would want a generator $g$ whose modeled distribution fits our dataset $data$, in other words, $P_{...
3
votes
1answer
1k views

What parameters can be tweaked to avoid a generator or discriminator loss collapsing to zero when training a DC-GAN?

Sometimes when I am training a DC-GAN on an image dataset, similar to the DC-GAN PyTorch example (https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html), either the Generator or ...
2
votes
0answers
47 views

Can GANs be used to generate matching pairs to inputs?

I have some limited experience with MLPs and CNNs. I am working on a project where I've used a CNN to classify "images" into two classes, 0 and 1. I say "images" as they are not actually images in the ...
3
votes
1answer
89 views

Other deep learning image generation techniques besides GANs?

Can you please point me to some resources about image genereation besides GANs? Are there any other techniques throughout history? How did idea of image generation evolved and how it started? I tried ...
3
votes
0answers
37 views

How do GANs create an image with specific characteristics?

I've seen GANs that do things like convert an image to a painting or this GAN here https://make.girls.moe/#/ that takes in a set of characteristics and generates a waifu with those characteristics. ...
0
votes
2answers
155 views

Which libraries can be used for image caption generation? [closed]

Which libraries can be used for image caption generation?
2
votes
2answers
117 views

How important is it that the generator of a generative adversarial network doesn't take in information about input classes?

I'm building a generative adversarial network that generates images based on an input image. From the literature I've read on GANs, it seems that the generator takes in a random variable and uses it ...
12
votes
1answer
1k views

Understanding notation of Goodfellow's GAN objective function

What is the meaning of $V(D,G)$? How do we get these expectation parts? I was trying to understand it following this article: Understanding Generative Adversarial Networks (D.Seita), but, after many ...
3
votes
0answers
28 views

How do we ensure that training GANs will fall in the desirable Nash equilibrium?

One Nash equilibrium of every GANs model has is when the generator creates perfect samples indistinguishable from the training data and the discriminator just output 1 with probability 1/2. And I ...
1
vote
1answer
166 views

How to get good results with GAN and some thousands of images?

I'm trying to generate images at minimum of size 128 x 128 with a Generative Adversarial Network. I already tried a SAGAN pytorch implementation, but I'm not very happy with results. The images look ...
3
votes
2answers
123 views

Do we also need to model a probability distribution for the decoder of a VAE?

I'm working on understanding VAEs, mostly through video lectures of Stanford cs231n, in particular lecture 13 tackles on this topic and I think I have a good theoretical grasp. However, when looking ...
1
vote
1answer
24 views

What is the goal of the model and is the training data relevant to that?

The model that we develop in artificial intelligence.What is its purpose,and what training data is relevant to it.
3
votes
3answers
2k views

Confusing on GAN loss function

I was trying to understand the loss function of GANs, while I found a little mis-match between different papers. This is the screen-shot from the original paper of Goodfellow at https://arxiv.org/...
3
votes
1answer
122 views

Why is the last layer of a DBN or DBM used for classification task?

I understand why deep generative models like DBN ( deep belief nets ) or DBM ( deep boltzmann machines ) are able to capture underlying structures in data and use it for various tasks ( ...
2
votes
1answer
159 views

Is there a mathematical example for Conditional Random Fields?

I am learning about probabilistic graphical models and I was wondering if there is an example explaining the math behind conditional random fields. Looking solely on the formula, I have no idea what ...
2
votes
0answers
56 views

What kind of distributions can be used to model discrete latent variables?

If we take the vanilla variational auto-encoder (VAE), we $p(z)$ is a Gaussian distribution with zero mean and unit variance and we approximate $p(z|x) \approx q(z|x)$ to be a Gaussian distribution as ...
6
votes
2answers
7k views

Why are Variational autoencoder's output is blurred while GANs output is crisp and has sharp edges?

I observed in several papers that the Variational autoencoder's output is blurred while GANs output is crisp and has sharp edges. Can someone please give some intuition why that is the case? I did ...
1
vote
0answers
218 views

Stack for Automatic 3D Mesh Generation

Gist: Should I use LISP for a part of the following project. What are the other options. Me and a friend are planning to create a 3D Modelling Agent where a designer can :- Specify constrains on how ...
1
vote
1answer
28 views

Adding voices to voice synthesis corpuses

If one uses one of the open source implementations of the WaveNet generative speech synthesis design, such as https://r9y9.github.io/wavenet_vocoder/, and trains using something like the CMU's arctic ...
2
votes
1answer
88 views

Why do we use $D(x \mid y)$ and not $D(x,y)$ in conditional generative adversarial networks?

In conditional generative adversarial networks (GAN), the objective function (of a two-player minimax game) would be $$\min _{G} \max _{D} V(D, G)=\mathbb{E}_{\boldsymbol{x} \sim p_{\text {data }}(\...
1
vote
1answer
95 views

How can AI be used to more reliably analyze and plan around the tie between climate and emissions?

Note to the Duplicate Police This question is not a duplicate of the Q&A thread referenced in the close request. The only text even remotely related in that other thread is the brief mention of ...
7
votes
2answers
429 views

What are the best machine learning models for music composition?

What are the best machine learning models that have been used to compose music? Are there some good research papers (or books) on this topic out there? I would say, if I use a neural network, I would ...
1
vote
1answer
824 views

Why do we need Upsampling and Downsampling in Progressive Growing of Gans

I was working recently on Progressive Growing of GANs (aka PGGANs). I have implemented the whole architecture, but the problem that was ticking my mind is that in simple GANs, like DCGAN, PIX2PIX, we ...
5
votes
1answer
3k views

Are deep learning models suitable for training with sparse data?

I am training a generative adversarial network (GAN) to generate images given edge histogram descriptor (EHD) features of the image. The EHD features are themselves sparse (meaning they contain a lot ...
2
votes
0answers
86 views

How do GAN's generator actually work?

I have implemented DCGAN's myself and have been studying GAN's for over a month now. Now I am implementing the pggans but I encountered a sentence When we measure the distance between the ...
12
votes
3answers
461 views

Can some one help me understand this paragraph from Nvidia's progressive GAN paper?

Furthermore, we observe that mode collapses traditionally plaguing GANs tend to happen very quickly, over the course of a dozen mini-batches. Commonly they start when the discriminator overshoots, ...
2
votes
0answers
373 views

Coding CGAN paper model in Keras

I was coding a CGAN model using Keras along with the paper (https://arxiv.org/pdf/1411.1784.pdf) and I wanted to try and match the models to exactly what the paper says. I knew the models presented in ...
4
votes
1answer
38 views

Looking to build, compile, and/or find dataset for serial-parallelized code examples

I'm looking to perform two tasks: Train a classifier to classify code as serial or parallel Train a generative algorithm to generate parallel code from serial For the first task a simple scraper ...
0
votes
2answers
119 views

Neural network to get input attributes using only the output value

I have an idea about how to use neural networks but I'm not sure if it is possible or not. In supervised learning we have a set of attributes labeled with an output value. I can use these set to ...
3
votes
1answer
865 views

How to evaluate the goodness of images generated by GANs?

As we all know, there has been tons of GAN variants featuring different aspects of the image generation task such as stability, resolution or the ability to manipulate images. However, it is still ...
1
vote
1answer
933 views

What is the purpose of the GAN?

The Generative Adversarial Network (GAN) is composed of a generator $G$ and a discriminator $D$. How do these two components interact? What is the intuition behind the GAN, its purpose, and how it is ...
2
votes
2answers
110 views

What are the possible social consequences of training neural networks with artificially generated data?

Machine learning models and, in particular, neural networks are trained with data often collected from the real world, such as images of real people. Meanwhile, neural networks (such as GANs) are also ...
20
votes
3answers
25k views

How can we process the data from both the true distribution and the generator?

I'm struggling to understand the GAN loss function as provided in Understanding Generative Adversarial Networks (a blog post written by Daniel Seita). In the standard cross-entropy loss, we have an ...

1
2