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
Artificial Intelligence

Top Questions

Ask Question
Active 1 Bountied Hot Week Month
31 votes
6 answers
12k views

Is the "Chinese room" an explanation of how ChatGPT works?

John Hausmann
  • 21
30 votes
3 answers
17k views

ChatGPT is aware of today's date

Amruth A
  • 109
12 votes
5 answers
2k views

Why is a bias parameter needed in neural networks?

Kostya
  • 2,261
3 votes
2 answers
581 views

Can LSTM model use ReLU or LeakyReLU as the activation funtion?

Brian O'Donnell
  • 1,678
5 votes
2 answers
193 views

Will the AI be able to formulate scientific principles or theories missed by humans in the future?

Rexcirus
  • 1,056
5 votes
1 answer
475 views

Will a CNN that is Group Equivariant always be better than a regular CNN?

fkybrd
  • 1
-3 votes
1 answer
388 views

Does GPT4 code more correctly than GPT3.5? [closed]

Universal_learner
  • 65
6 votes
2 answers
259 views

Is GPT-4 based on GPT-3 or was it trained from the scratch?

Volker Siegel
  • 272
5 votes
2 answers
367 views

Term for algorithms that are not trained

nammerkage
  • 176
0 votes
0 answers
485 views

openai.error.RateLimitError

Ferda-Ozdemir-Sonmez
  • 133
1 vote
2 answers
471 views

How is GPT 4 able to solve math?

Jaume Oliver Lafont
  • 696
0 votes
1 answer
179 views

How is InstructGPT a fine-tuned version of GPT-3 and at the same time has fewer parameters than the original GPT3?

nbro
  • 37k
1 vote
2 answers
171 views

Open-source vocal cloning (speech-to-speech neural style transfer)

Hans-Peter Schrei
  • 197
0 votes
0 answers
277 views

How important is to fix this common Tensorflow warning?

Mah Neh
  • 79
1 vote
1 answer
112 views

How does transformer models like GPT generate valid meaningful response for meaningless garbage input?

BlueSnake
  • 57
1 vote
1 answer
109 views

Creating a support chat bot for my business

kokumajutsu
  • 31
1 vote
1 answer
149 views

How is ChatGPT trained?

Rexcirus
  • 1,056
2 votes
1 answer
116 views

Why is soft actor critic an off policy scheme?

Hans-Peter Schrei
  • 197
3 votes
2 answers
67 views

What makes the approximation capabilities of neural networks different than something like, say, Fourier series?

Luke
  • 36
1 vote
2 answers
49 views

How to detect outlier images?

NikoNyrh
  • 605
2 votes
1 answer
75 views

How could chatGPT avoid consuming what it produces

zzzgoo
  • 123
2 votes
1 answer
74 views

How do the "built on ChatGPT" apps work in general at a high level?

Volker Siegel
  • 272
0 votes
1 answer
62 views

Repainting a picture in the style of some painter (or of another picture)

Broele
  • 381
3 votes
1 answer
60 views

What is meant by "Deep Learning models are not understood"?

chessprogrammer
  • 2,005
1 vote
1 answer
76 views

Transformers: how does stacking work? [closed]

Jakub Podolak
  • 36
1 vote
1 answer
56 views

Can NEAT produce output which has no connection with any other node?

Neil Slater
  • 26.5k
1 vote
2 answers
70 views

Why optimise log p(x) rather than log p(x|z) in a Variational AutoEncoder?

Kostya
  • 2,261
1 vote
1 answer
67 views

What exactly is meant as losing the "competitive moat" when sharing AI models?

Rexcirus
  • 1,056
0 votes
1 answer
81 views

What is the significance of move 37? (to a non go player)

chessprogrammer
  • 2,005
4 votes
1 answer
80 views

What can GPT-4 do linguistics-wise?

Anixx
  • 211
1 vote
1 answer
58 views

Is understanding understandable?

Rexcirus
  • 1,056
0 votes
1 answer
45 views

Seq2seq with RNNs, how is the training loop performed?

Hans-Peter Schrei
  • 197
0 votes
0 answers
94 views

Is google able to recognize Chat GPT content?

Fedeco
  • 101
1 vote
2 answers
55 views

Is data useless for a neural network if some inputs are derivatives of other inputs?

DeepQZero
  • 1,122
0 votes
1 answer
55 views

Is it possible for a GPT model to run in a distributed way?

Augusto Vasques
  • 121
0 votes
1 answer
54 views

How to approach a toy classification problem using a neural network?

Jaume Oliver Lafont
  • 696
1 vote
1 answer
67 views

Why is Soft Q Learning not an Actor Critic method?

mohottnad
  • 561
0 votes
1 answer
63 views

I understand a neural network is a program, or something similar, but what exactly does it look like while it's learning?

user253751
  • 659
2 votes
0 answers
80 views
+100

Reverse Process in Diffusion Model Doesn't Return Original Image

cabralpinto
  • 21
2 votes
0 answers
76 views

How code analysis part of ChatGPT works and trained

BRUCE
  • 121
1 vote
1 answer
46 views

Large Language Models vs Tabular Data

Ggjj11
  • 149
1 vote
1 answer
59 views

SparseGPT code reproduction

user68072
  • 33
0 votes
1 answer
45 views

Where to find the source code for the research paper "Attention is all you need"?

Hans-Peter Schrei
  • 197
0 votes
0 answers
74 views

When I start to train my model in stable diffusion, the following problem appears: Applying cross attention optimization (Doggettx) [closed]

Антон
  • 1
0 votes
1 answer
73 views

Keypoint generation in 3D point clouds with Deep Learning

fkybrd
  • 1
1 vote
1 answer
34 views

What is the appropriate threshold for accuracy in logistic regression?

chessprogrammer
  • 2,005
0 votes
1 answer
34 views

Should softmax be in the model or in the loss function?

chessprogrammer
  • 2,005
0 votes
0 answers
68 views

Tool for detecting AI Generated code?

Haseeb Mir
  • 101

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

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.