Aray Karjauv's user avatar
Aray Karjauv's user avatar
Aray Karjauv's user avatar
Aray Karjauv
  • Member for 6 years
  • Last seen more than a week ago
8 votes
Accepted

Can someone explain R1 regularization function in simple terms?

4 votes

Why is KL divergence used so often in Machine Learning?

4 votes

What is Lipschitz constraint and why it is enforced on discriminator?

4 votes
Accepted

Does ChatGPT type slowly on purpose or is it computing?

4 votes

What are the consequences of layer norm vs batch norm?

3 votes
Accepted

GAN model predictions before training is predictable

3 votes

Does the performance of a model increase if dropout is disabled at evaluation time?

3 votes

What are examples of approaches to create an AI for a fighting robot in an MMO game?

3 votes
Accepted

An explanation involving the sign activation, its affect on the loss function, and the perceptron and perceptron criterion: what is this saying?

2 votes
Accepted

Why adversarial images are not the mainstream for captchas?

2 votes

How to calculate the gradient penalty proposed in "Improved Training of Wasserstein GANs"?

2 votes

how produce image of face working with AI

2 votes

Does the output layer in a deep neural network need an activation function?

2 votes
Accepted

What does all the formula and pictures mean?

2 votes
Accepted

GANs: Should Generator update weights when Discriminator says false continuously

2 votes

Improving DQN with fluctuations

2 votes
Accepted

How to tell a neural network that: "your i-th input is special"

2 votes
Accepted

How can I determine whether a video's frame is realistic (was recorded by a camera) or contains computer-generated graphics?

1 vote

Explain the difference in graphical patterns between discriminator fake loss and generator loss in GAN

1 vote

How is the probability transition matrix populated in the Markov process (chain) for a board game?

1 vote

Is reinforcement learning suited for real-time systems?

1 vote

What is the right way to train a generator in a GAN?

1 vote

How should I define the reward function to solve the Wumpus game with deep Q-learning?

1 vote

Where does the so-called 'loss' / 'loss function' fit into the idea of a perceptron / artificial neuron (as presented in the figure)?

1 vote

Why do we commonly use the $\log$ to squash frequencies?

1 vote

How would you shape a reward function if there was four quantities to optimize?

1 vote
Accepted

Should I use an unsupervised approach or train a classifier with many classes to build a deep image feature extractor?

1 vote

What are the iid random variables for a dataset in the GAN framework?

1 vote

Is there any metric for calculating how natural a single image is given a dataset of the same class images?

1 vote

Are there architectures to generate pictures from four labels? (VAEs, GANs)