Artificial Intelligence

Scholar

 Scholar
Ask a question and accept an answer.
Awarded 2307 times.
How could chatGPT avoid consuming what it produces
Awarded 2 hours ago
How to convert my test data in the same dimensionality as my train data
Awarded 3 hours ago
Will the AI be able to formulate scientific principles or theories missed by humans in the future?
Awarded 14 hours ago
Is GPT-4 based on GPT-3 or was it trained from the scratch?
Awarded yesterday
Going beyond intent classification
Awarded yesterday
Which loss / activation function with 2 classes that do not occur often and do not sum to one?
Awarded Mar 20 at 3:32
What is meant by "Deep Learning models are not understood"?
Awarded Mar 17 at 12:05
What exactly is meant as losing the "competitive moat" when sharing AI models?
Awarded Mar 17 at 4:27
Negative sampling in batch or entire dataset?
Awarded Mar 16 at 8:43
Is there a mathematical proof that a binary neural network can approximate any function with arbitrary accuracy?
Awarded Mar 14 at 2:56
Would self-hosting ChatGPT be feasible, w.r.t. computation costs?
Awarded Mar 13 at 11:55
How to reduce the number of clusters produced by the Markov Clustering Algorithm?
Awarded Mar 12 at 15:26
I understand a neural network is a program, or something similar, but what exactly does it look like while it's learning?
Awarded Mar 11 at 13:11
I am confused of derivation steps of MAP for linear regression
Awarded Mar 10 at 2:06
How to structure the input data for non-vision deep reinforcement learning?
Awarded Mar 8 at 13:58
Can NEAT produce output which has no connection with any other node?
Awarded Mar 8 at 13:01
Does the position of the tokens in Vision Transformer matter?
Awarded Mar 8 at 10:58
Resources for NLP [closed]
Awarded Mar 7 at 16:16
How to expand an agent's action space with more actions?
Awarded Mar 3 at 7:31
Is data useless for a neural network if some inputs are derivatives of other inputs?
Awarded Mar 2 at 15:10
Transformers: how does stacking work? [closed]
Awarded Mar 1 at 16:26
Is the "Chinese room" an explanation of how ChatGPT works?
Awarded Mar 1 at 7:35
What is the appropriate threshold for accuracy in logistic regression?
Awarded Feb 28 at 5:05
Why do training and fixing a reservoir yield very similar results (in an echo state network)?
Awarded Feb 28 at 2:26
What is the intuition behind self-attention?
Awarded Feb 27 at 20:42
Are there any advantages of encoding an image as a graph to use in Graph Convolutional Networks?
Awarded Feb 27 at 15:57
What is the significance of move 37? (to a non go player)
Awarded Feb 27 at 3:47
How is InstructGPT a fine-tuned version of GPT-3 and at the same time has fewer parameters than the original GPT3?
Awarded Feb 26 at 0:48
ChatGPT claims that it doesn't get information from anywhere, so can't say why it gave a blatantly false statement. How is that possible?
Awarded Feb 24 at 21:55
Why is it called a Seq2Seq model if the output is just a number?
Awarded Feb 24 at 18:28
Does object detection for single-class images have any advantages over classification?
Awarded Feb 24 at 6:32
Why final memory state equals to the last hidden state of entire hidden state sequence?
Awarded Feb 23 at 8:17
How does mixing and matching encoders and decoders work in image segmentation?
Awarded Feb 22 at 16:33
What kind of algorithm to use
Awarded Feb 21 at 20:35
Does ChatGPT type slowly on purpose or is it computing? [duplicate]
Awarded Feb 21 at 19:42
How to account for a numeric variable in a state in RL?
Awarded Feb 21 at 16:41
Explanation of Cross-Modality Linear Transformer
Awarded Feb 20 at 9:17
Machine learning applied to space-time diagrams of cellular automata
Awarded Feb 20 at 6:40
What is the correct partial derivative of $Y^c$ with respect to $A_{ij}^{kc}$?
Awarded Feb 20 at 0:04
Are there neurons in CNNs? [duplicate]
Awarded Feb 19 at 16:47
Which Q function do we use to make our policy when using double Q learning?
Awarded Feb 19 at 13:04
"Attention is all you need" paper : How are the Q, K, V values calculated?
Awarded Feb 17 at 14:57
What is the motivation for using Q-Learning in RL?
Awarded Feb 14 at 19:47
Are GPT-3.5 series models based on GPT-3?
Awarded Feb 13 at 8:08
What background should I have before starting to fine tune a Large Language Model?
Awarded Feb 12 at 21:20
What causes ChatGPT to generate responses that refer to itself as a bot or LM?
Awarded Feb 10 at 20:20
Why does linearly decreasing batch sizes result in exponentially increasing training times?
Awarded Feb 7 at 16:55
What exactly is the future of mathematical analysis that can be dealt with AI (especially in the automated theorem proving)?
Awarded Feb 5 at 9:51
How can I get Q-Learning (1 step off policy) update from n-step off policy learning update?
Awarded Feb 5 at 9:42
High precision and low recall results. What does it mean?
Awarded Feb 4 at 19:18
Did old-fashioned, rule-based systems die out when statistical learning broke through into NLP?
Awarded Feb 4 at 13:04
Why does A2C use the actual returns from an episode in calculating the advantage?
Awarded Feb 2 at 20:57
How to handle the size difference of highway network or residual network in cnn?
Awarded Feb 2 at 20:47
What makes reproducing a model like GPT3/GPT3.5/ChatGPT difficult?
Awarded Feb 2 at 10:10
Is Momentum a form of inexact line search?
Awarded Jan 31 at 13:32
YOLO v1 confidence score during inference
Awarded Jan 30 at 17:02
What is the difference between Neurosymbolic AI and Transformer AI
Awarded Jan 27 at 16:26
Please help me understand the role of loss function in neural networks
Awarded Jan 27 at 4:19
Would it be possible to involve a proof assistant in the process of training a LLM?
Awarded Jan 26 at 13:33
What is the correct loss function for binary classification: Cross entropy or Binary cross entropy?
Awarded Jan 25 at 12:20
1
2 3 4 5
…
39

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.