Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community
Anybody can ask a question
Anybody can answer
The best answers are voted up and rise to the top

Top Questions

1 vote
1 answer
41 views

possible to combine multiple labeled objects as one object?

5 votes
1 answer
224 views

How does the optimization process in hindsight experience replay exactly work?

1 vote
2 answers
72 views

Late Onset Augmentation

0 votes
0 answers
33 views

Nonlinear Poisson regression with two independent variables

0 votes
1 answer
87 views

Having the negative cases in the same batch vs. shuffling the dataset

3 votes
1 answer
774 views

What are the keys and values of the attention model for the encoder and decoder in the "Attention Is All You Need" paper?

0 votes
0 answers
5 views

XML Input to assist in composing muusic

1 vote
1 answer
59 views

Which type of Machine Learning is used in robots?

4 votes
2 answers
258 views

Does increasing the number of Q functions in Q-Learning scale?

-1 votes
1 answer
50 views

Does a decoder in transformer model generate output embeddings like the following?

1 vote
0 answers
26 views

Do diffusion models take a long time to train?

0 votes
0 answers
14 views

What kind of data has to be collected for Named Entity Recognition

0 votes
0 answers
13 views

Can we generate High Quality and Realistic videos from text or not? If not then why and if yes then how?

2 votes
2 answers
3k views

How to improve the performance of Easy OCR

-1 votes
0 answers
11 views

Few Shot Prompt [closed]

0 votes
1 answer
119 views

How to produce documents like factset blackline?

0 votes
0 answers
10 views

Bellman equation for MRP

0 votes
0 answers
17 views

Same prediction result with little probabilities change

2 votes
1 answer
115 views

Bellman equation and inverse matrix method

3 votes
2 answers
348 views

How can we derive a Convolution Neural Network from a more generic Graph Neural Network?

1 vote
1 answer
30 views

How do we get from types of activation functions to fitting lines to our data?

0 votes
1 answer
69 views

What should be taken as random variables in the distributions of datasets?

-1 votes
0 answers
13 views

ModuleNotFoundError: No module named ‘torch.distributed.algorithms.join [closed]

1 vote
1 answer
35 views

Distribution of a log-normal random variable with fixed dimension

0 votes
1 answer
19 views

Retaining document level security of a CMS

0 votes
0 answers
9 views

Classical architecture of autoencoder neural networks

26 votes
4 answers
14k views

Why do ChatGPT “jailbreaks” work?

0 votes
0 answers
29 views

Can you illustrate how the weights in transformer model generated from a training sentence can be generalized to an unseen test sentence?

3 votes
1 answer
292 views

NEAT can't solve XOR completely

2 votes
1 answer
103 views

Can we solve the environment with only the linear and angular position through Q-Learning?

0 votes
0 answers
29 views

Intentionally corrupting LLM weights (lobotomy)

1 vote
0 answers
10 views

Neural network architecture or code for style transfer with aligned data

2 votes
1 answer
888 views

Periodic Pattern in Validation Loss Curve

0 votes
0 answers
7 views

Example VQ-VAE code for audio in paper "Neural Discrete Representation Learning"

0 votes
1 answer
37 views

Methods of constructing input and ouput vectors in Reinforcement Learning with approximation function learning?

0 votes
0 answers
14 views

Masking during Instruction Tuning for LLM finetuning

0 votes
1 answer
31 views

why by adding additional information as number of sequence on dataset can avoid overfitting

4 votes
1 answer
468 views

How did the OpenAI 5 for Dota concatenate units?

1 vote
0 answers
57 views

When can we unnest the minimizations/recursions in an value function(bellman optimality equation)?

0 votes
1 answer
81 views

How do we make our outputs to have the same size as the true mask?

1 vote
1 answer
79 views

What does "All store and access operations (for S(t) , A(t), and R(t)) can take their index mod n + 1" mean?

1 vote
2 answers
192 views

What kind of algorithm or approach can I use to find a specific type of object in an image?

1 vote
2 answers
83 views

References on Theoretical Bandit Problem

52 votes
2 answers
43k views

How does ChatGPT retain the context of previous questions?

1 vote
2 answers
1k views

Why should one expect the backward pass to take twice as long as the forward pass?

1 vote
1 answer
54 views

OpenAI Gym implementation of the delayed rewards

-1 votes
0 answers
11 views

extractive and generative q&a systems

1 vote
1 answer
85 views

DQN with experience history to learn from already saved - which reward should I take?


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