Top Questions

5 votes
1 answer
607 views

How can the discriminator determine the sample is fake or real?

3 votes
1 answer
240 views

What do you mean by "updating based on a training example/batch" in Gradient Descent?

2 votes
2 answers
94 views

What's the best criterion for evaluating activation maps in a CNN?

1 vote
1 answer
99 views

Unclear paragraph in Sutton-Barto on exploration/exploitation relating to bandit like decision tasks [closed]

2 votes
1 answer
113 views

REINFORCE with Baseline update rule

0 votes
1 answer
129 views

Getting started with training local LLM using python [closed]

3 votes
1 answer
66 views

Are the Dot Product and Tensor Product the same thing in Machine Learning?

2 votes
2 answers
106 views

What is the state space of digit recognition agent on a grid of 28 x 28 pixels?

3 votes
1 answer
98 views

How does changing the order of a sequence of rewards affect the cumulative discounted reward

1 vote
1 answer
58 views

Is there a theoretical way to determine the best learning rate for gradient descent if the function is a simple known polynomial?

2 votes
1 answer
72 views

Should I use RL for this allocation problem and, if yes, which RL approach?

0 votes
1 answer
90 views

Why does the latent space in Stable Diffusion have a shape of 64x64x3?

2 votes
2 answers
85 views

How Xavier Initialization formula works

1 vote
3 answers
83 views

How to force LLM (like OpenAI ChatGPT) to output a variable list of values? [closed]

1 vote
1 answer
57 views

Activation function intuition question

-1 votes
1 answer
71 views

Is there any example of a Markov Decision Process (MDP) with infinite number of states?

3 votes
2 answers
55 views

How does diffusion based text-to-image generation models Mathematically classify inputs to outputs?

0 votes
2 answers
68 views

Is it legitimate to train a model on a benchmark dataset and use this model only for labeling another datasets

2 votes
1 answer
64 views

How are POMDPs solved in practice?

1 vote
1 answer
60 views

Why aren't encoders decoders trivial?

1 vote
1 answer
77 views

Is there any advantage of genetic algorithm (or programming) over Neural Networks? [closed]

2 votes
1 answer
74 views

Neural Networks are universal approximators? - Exercice 20.1 UML

2 votes
1 answer
57 views

What are meaning of parameters $\theta$ in this context?

0 votes
1 answer
55 views

Why would balancing be so helpful when the imbalance is minimal?

1 vote
2 answers
68 views

Attention with Recurrent Neural Networks

1 vote
1 answer
68 views

What does the notation $\hat{A}_t\left(s_{0: \infty}, a_{0: \infty}\right)$ appearing in Generalized Advantage Estimation mean?

0 votes
2 answers
47 views

What is the logic in including/not including subscript $\pi$ in in "E" for value functions? [closed]

2 votes
1 answer
77 views

What is the meaning of log p(x) in VAE math and why is it constant

1 vote
1 answer
46 views

What is the matrix representation of a dilated convolution?

2 votes
1 answer
58 views

Can you explain the Hinton's comment "Rprop is equivalent to using the gradient, but also dividing by the size of the gradient"?

0 votes
1 answer
58 views

What does it mean if I trained my model with more steps per epoch than the total number of training images I have?

1 vote
2 answers
57 views

Why is the cross entropy formula different from the binary cross entropy?

0 votes
1 answer
73 views

Are there cases where Variational Auto-Encoders (VAE's) are preferred to other techniques?

1 vote
1 answer
55 views

Tabular Q-Learning: Is a variable for "action_history" needed for backpropagating the q-value for all previous actions?

0 votes
1 answer
55 views

Does ResNext split data or copy it?

2 votes
1 answer
52 views

How does reward work while training a Reinforcement Learning agent?

2 votes
1 answer
52 views

Is it possible to describe wordle as a multi armed bandit problem?

0 votes
0 answers
66 views

When oultining dangers of AI breakthroughs, is there mislook bias to search in the technology itself rather than in human nature? [closed]

1 vote
1 answer
40 views

Marking object on a map from the image

1 vote
1 answer
51 views

When is it non-Markovian?

0 votes
0 answers
65 views
+100

NEAT program learns slowly and gets completely stuck

0 votes
0 answers
63 views

Where do you keep track of Chat History for an LLM Chat Application?

0 votes
1 answer
49 views

Handling Variable Output Token Dimensionality in Transformer Decoders During Inference

1 vote
1 answer
62 views

How does using the ELBO in VAEs make the problem tractable?

1 vote
1 answer
47 views

Batch wise Inference to speed up Muzero's MCTS [closed]

1 vote
1 answer
35 views

Is "The Dimpled Manifold Hypothesis" correct to say this about autoencoders?

0 votes
1 answer
57 views

I would love to know to spot where the ball is in the picture [closed]

1 vote
2 answers
43 views

Does transformers' self-attention mechanism process tokens independently, or entire sequence at a time?


Looking for more? Browse the complete list of questions, or popular tags. Help us answer unanswered questions.