Skip to main content
OverflowAI is here! AI power for your Stack Overflow for Teams knowledge community. Learn more

Top Questions

0 votes
0 answers
1 view

Eliminating images from AI responses in ChatGPT

0 votes
0 answers
2 views

Why people always use l2 loss in Neural Tangent Kernel and other neural network theory?

0 votes
2 answers
91 views

Performance of augmented dataset with or without original images

0 votes
0 answers
5 views

How are experienced and learned situations being stored?

0 votes
1 answer
14 views

Violation of Markov property

0 votes
0 answers
17 views

Structure and parameters of modern AI-baed chess engines

1 vote
1 answer
82 views

Why do we use $q_{\phi}(z \mid x^{(i)})$ in the objective function of amortized variational inference, while sometimes we use $q(z)$?

-1 votes
0 answers
15 views

Confusing statement in Sutton-Barto on trajectory sampling

-1 votes
1 answer
41 views

Can anyone please explain the Recurrent Neural Network calculation shown in the picture?

1 vote
1 answer
31 views

Why do we need complex neural network designs?

2 votes
1 answer
106 views

Can we implement a memory in a REINFORCE algorithm for RL?

0 votes
1 answer
180 views

In this paper, if region $R_{2}$ moves in a sliding window manner, won't the saliency map have a smaller size than the original image?

1 vote
1 answer
21 views

Why soft Bellman backup operator is converged in tabular settings?

1 vote
1 answer
479 views

Handling imbalanced data with multiple targets

0 votes
0 answers
20 views

Confusing statement in Sutton-Barto on expected versus sample updates

4 votes
2 answers
2k views

How to perform gradient checking in a neural network with batch normalization?

0 votes
0 answers
11 views

What is the main way of using ns3-ai to develop DQN algorithms? How does python interact with NS3 in this case?

1 vote
1 answer
112 views

What is x, y, p(x), p(y) in generative model domain?

0 votes
1 answer
283 views

Hot to calculate Maximum Normalized log Probability for Active Learning with BERT

0 votes
1 answer
19 views

Sparse Cross Entropy

11 votes
2 answers
5k views

Can someone explain R1 regularization function in simple terms?

0 votes
0 answers
22 views

Are there LLMs that are allowed time to contemplate freely?

0 votes
0 answers
12 views

How Does AI-Generated Content Differ From Human-Written Content?

0 votes
3 answers
2k views

Why does Google Translate produce two different translations for the same Chinese text?

0 votes
1 answer
15 views

Could someone give a simple example of nondeterministic sensing?

0 votes
0 answers
6 views

Is it Possible to fit a sklearn model using a excel spreadsheet

0 votes
0 answers
10 views

Reinforcement Learning Gymnasium ValueError

0 votes
0 answers
13 views

Q-Learning conditions for convergence and ergodicity

0 votes
1 answer
21 views

Reference request: data efficiency of LLM pre-training

0 votes
1 answer
65 views

How can I solve a classification problem where the label for the same input is probabilistic?

0 votes
1 answer
15 views

Using additional parameters in PDDL precondition and effects of actions

2 votes
1 answer
164 views

How to Represent a Multi-Feature Input Vector in a Neural Net

0 votes
1 answer
14 views

Determining optimal data size for generalization in transformer encoders, particularly for Time-Series signal data

4 votes
2 answers
283 views

Are Genetic Algorithms suitable for a problem with a non-unique optimal solution?

3 votes
2 answers
396 views

Why must the value of a state under an optimal policy equal the expected return for the best action from that state?

1 vote
1 answer
671 views

How to scale all positive continuous reward?

3 votes
1 answer
2k views

Is it possible to train an AI to bring a picture story in the correct order (correct story flow)?

0 votes
0 answers
23 views

Neural Network with Incorrect Calculation Better than Correct One

0 votes
1 answer
51 views

Is knowing the class of probability density function mandatory for explicit density estimation?

0 votes
2 answers
310 views

ML-based algorithm/software for solving a sudoku puzzle a human way

0 votes
1 answer
96 views

What would be a good cost function based on both saliency-maps and labels?

0 votes
0 answers
10 views

Minimum remaining values heuristic more powerful than degree heuristic

2 votes
1 answer
114 views

Which is the probability of JohnCalls given Burglary? Why?

0 votes
0 answers
31 views

Is there any offline AI solution integrated with OS?

0 votes
0 answers
21 views

Why fine tuning does not work as well as RAG?

0 votes
1 answer
133 views

Can you make Q&A language model stay on topic?

0 votes
0 answers
20 views

No matter how I change a loss function I get it equal to infinity

0 votes
1 answer
49 views

How can I get started with LLMs?


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