Artificial Intelligence

Revival

 Revival
Answer more than 30 days after a question was asked as first answer scoring 2 or more. This badge can be awarded multiple times.
Awarded 446 times.
Why use a "square root" in the scaled dot product
Awarded Nov 29 at 15:38
Is a VGG-based CNN model sometimes better for image classfication than a modern architecture?
Awarded Nov 11 at 4:10
Does it make sense to apply batch normalization to a batch size of 1?
Awarded Nov 6 at 8:27
Why class embedding token is added to the Visual Transformer?
Awarded Nov 3 at 9:33
Is Christopher Bishop's "Pattern Recognition and Machine Learning" out of date in 2018?
Awarded Nov 1 at 13:41
Why can neural networks generalize at all?
Awarded Nov 1 at 8:46
Super Resolution CNN generates black dots on output images
Awarded Oct 30 at 8:31
How to calculate the advantage in policy gradient functions?
Awarded Oct 24 at 8:21
How exactly does Keras calculate the validation accuracy?
Awarded Sep 4 at 8:47
Are there some known neural networks that, given an input image, can generate a similar image, with the same topic?
Awarded Sep 4 at 0:26
How to manage high numbers of input layer data points
Awarded Aug 26 at 8:07
why cross entropy loss has to be multiplied by a batch size during an evaluation in transformer model?
Awarded Aug 15 at 14:21
What temperature would you recommend for the chatgpt api?
Awarded Aug 14 at 9:04
Why does AlphaZero not use vanilla MCTS?
Awarded Jul 28 at 8:40
Is there a proper initialization technique for the weight matrices in multi-head attention?
Awarded Jul 26 at 8:50
Should minimax with alpha beta pruning depth be an odd number?
Awarded Jul 20 at 4:26
Why do we need RL in RLHF?
Awarded Jul 9 at 22:27
Why is breadth-first search only optimal when the cost solution is a non-decreasing function?
Awarded Jul 6 at 18:55
How do I use GPT-2 to summarise text?
Awarded Jun 21 at 11:10
Whys and Why-nots using Rust for AI
Awarded Jun 14 at 22:21
Should batch-normalization/dropout/activation-function layers be used after the last fully connected layer?
Awarded Jun 3 at 13:17
Which of the following probability distribution is generating an iid dataset?
Awarded May 30 at 18:32
How can GPT-3 be used for designing electronic circuits from text descriptions?
Awarded May 23 at 21:26
Last linear layer of the decoder of a transformer
Awarded May 16 at 13:57
Sutton and Barto 2nd Edition Exercise 13.1
Awarded May 8 at 10:48
Meaning of roles in the API of GPT-4/ChatGPT (system/user/assistant)
Awarded May 7 at 23:56
Is whisper.ai non-deterministic?
Awarded May 7 at 13:32
How to extract the main text from a formatted text file?
Awarded May 1 at 16:22
How does GPT use the same embedding matrix for both input and output?
Awarded Apr 25 at 17:10
Can I always use "encoding" and "embedding" interchangeably?
Awarded Apr 14 at 2:31
How much of the ChatGPT output is copied from its training set (vs. being abstractively generated)?
Awarded Mar 14 at 9:25
How do I get chatGPT to include custom knowledge?
Awarded Mar 13 at 10:21
Why don't people use nonlinear activation functions after projecting the query key value in attention?
Awarded Mar 9 at 9:10
Rebuild Tiktok Manga/Anime AI model
Awarded Mar 8 at 15:41
How does non-max suppression work when one or multiple bounding boxes are predicted for the same object?
Awarded Mar 8 at 14:03
Is there an AI tool to reverse engineer scanned data to obtain its CAD file?
Awarded Mar 8 at 11:41
Does the position of the tokens in Vision Transformer matter?
Awarded Mar 6 at 17:16
How can I train a RL agent to play board games successfully without human play?
Awarded Feb 19 at 0:36
Genetic Algorithm Python Snake not improving
Awarded Feb 10 at 18:18
Training RNN's on text: Can you use an ASCII encoding just as well as a one-hot character encoding?
Awarded Feb 8 at 20:57
Reinforcement Learning with PPO - entropy loss dropping, but so is performance. Why?
Awarded Feb 3 at 1:42
What causes ChatGPT to generate responses that refer to itself as a bot or LM?
Awarded Feb 2 at 22:31
What is the exact role of model $p_\theta$ in diffusion models for the reverse process?
Awarded Jan 24 at 9:56
What are the main differences between YOLOv3 and RetinaNet object detection algorithms?
Awarded Jan 21 at 19:57
How to implement a neural network for Flappy Bird in Python?
Awarded Jan 17 at 2:11
Mapping input vectors of variable length to output vectors of variable lengths with dummy variables
Awarded Jan 12 at 9:33
How many types of variational auto-encoders are there?
Awarded Jan 8 at 22:15
What is the most important predecessor of the transformer model?
Awarded Dec 15, 2022 at 19:21
Why is the time complexity of the Triplet Loss $O(N^3)$
Awarded Nov 23, 2022 at 20:21
Aside from dice score, what other good metrics are used to evaluate segmentation models?
Awarded Nov 16, 2022 at 15:45
Does this prove AI Safety is undecidable?
Awarded Nov 11, 2022 at 16:18
Minimax combined with machine learning to determine if a path should be explored
Awarded Nov 8, 2022 at 7:43
How do neural network topologies affect GPU/TPU acceleration?
Awarded Oct 30, 2022 at 12:15
Detect patterns in sequences of actions
Awarded Oct 28, 2022 at 16:31
What are the differences between a knowledge base and a knowledge graph?
Awarded Oct 28, 2022 at 5:27
How can a neural network distinguish a rotated 6 and 9 digits?
Awarded Oct 26, 2022 at 9:07
Can off-policy algorithms benefit from the parallelization?
Awarded Oct 24, 2022 at 18:15
Sutton and Barto 2nd Edition Exercise 13.1
Awarded Oct 23, 2022 at 11:35
Why is there tanh(x)*sigmoid(x) in a LSTM cell?
Awarded Oct 22, 2022 at 17:01
At what point are MCTS results discarded in AlphaZero Training?
Awarded Oct 11, 2022 at 10:18
1
2 3 4 5
…
8

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.