Skip to main content
Artificial Intelligence

Scholar

 Scholar
Ask a question and accept an answer.
Awarded 2660 times.
"Window Pane" pattern when training CycleGAN
Awarded Sep 8 at 9:51
What is the definition of a perceptron?
Awarded Sep 7 at 19:42
Why are biased results from ML models bad?
Awarded Sep 7 at 17:47
Is the feed forward layer in the last encoder block of a transformer unnecessary?
Awarded Sep 6 at 10:42
What is the difference between transformer types?
Awarded Sep 3 at 0:19
Deciphering terse CNN specifications
Awarded Sep 1 at 22:18
Does someone know when GPT5 will be publicly available?
Awarded Sep 1 at 0:04
How does a transformer choose the next word concretely?
Awarded Aug 29 at 16:16
Make a neural network automatically discover classes?
Awarded Aug 24 at 18:47
Which batch size is optimal for my neural network?
Awarded Aug 23 at 9:55
Role of time embedding in flow matching
Awarded Aug 22 at 13:13
How to convert a positionally encoded predicted embedding from a decoder to its matching token?
Awarded Aug 16 at 7:04
Treating binary classification as 3 class problem with two cutoffs -- what metric to use?
Awarded Aug 14 at 22:15
Matrix Multiplication using a Neural Network
Awarded Aug 14 at 14:04
can we apply soft actor critic to language model preference optimization? [closed]
Awarded Aug 11 at 19:49
How to perform inference pn a mixture of Gaussian models?
Awarded Aug 11 at 8:06
AlphaProof and infinitary combinatorics [closed]
Awarded Aug 8 at 13:20
How come machines have become intelligent? [duplicate]
Awarded Aug 6 at 18:51
Why isn’t this formula used at all?
Awarded Aug 1 at 13:13
Is there a theoretically optimal input range for neural networks?
Awarded Aug 1 at 12:55
Dealing with likely class imbalance for unlabeled test data
Awarded Jul 30 at 22:41
Understanding the Intuition Behind Formulas in "Epistemic Neural Networks" [closed]
Awarded Jul 30 at 14:19
Why is gradient clipping not preventing my gradient descent from going out of bounds?
Awarded Jul 26 at 13:47
Why does KNN Model return 99% accuracy on dataset with default parameters? [closed]
Awarded Jul 22 at 4:08
Why does generalization error's integral integrate over both X and Y, not just X?
Awarded Jul 20 at 17:10
Please help me understand constant-α Monte Carlo method
Awarded Jul 19 at 0:16
Does probability flow ODE trajectory (in the context of diffusion models) represents a bijective mapping between any distribution to a gaussian? [closed]
Awarded Jul 17 at 7:30
Classifier-Free-Guidance with Transformers
Awarded Jul 16 at 13:21
How does BackProp avoid bias for the last input used for training?
Awarded Jul 14 at 20:26
Is a linear regression model able to figure out the relation of division among two features?
Awarded Jul 11 at 22:19
How is the bidirectional context achieved in BERT?
Awarded Jul 11 at 1:27
Actor Critic need to find the goal to have good update and suceed?
Awarded Jul 8 at 16:01
Why gradients are used in Layer-wise Relevance Propagation (LRP)?
Awarded Jul 3 at 16:51
Do we use RL to train ANNs, or use ANNs as par of a RL solution?
Awarded Jul 2 at 14:11
In multi-class classification, how accurate can the model be if there's class imbalance?
Awarded Jul 1 at 19:49
How would I approach finding the source code for the paper that is being discussed in this article?
Awarded Jun 30 at 21:34
Filter scientific papers based on abstract information
Awarded Jun 28 at 20:37
How to choose the right size LLM for inference to balance latency and accuracy, among several LLMs from 3B through 140B?
Awarded Jun 28 at 1:03
How big the context can be using HuggingFace models?
Awarded Jun 25 at 12:02
How would I train a neural net on multiple different computers?
Awarded Jun 20 at 15:36
Vision transformer for image segmentation
Awarded Jun 20 at 12:33
Difference between .pt and .pth extensions in PyTorch model saving [closed]
Awarded Jun 16 at 4:25
Can we use the capabilities of quantum computing to enhance neural networks?
Awarded Jun 15 at 8:26
How to use the tf.image.SSIM function [closed]
Awarded Jun 13 at 13:25
Dot notation for matrix element index in formula of word2vec embedding calculation
Awarded Jun 9 at 14:45
How is it possible that RAG embeddings implemented with a different embedding model than the pre-trained LLM can work?
Awarded Jun 8 at 22:06
What is the formula for $VC(H)$ in Computational Learning Theory? [duplicate]
Awarded Jun 8 at 16:25
Does a vector database maintain pre-vector chunked data for RAG systems?
Awarded Jun 7 at 15:56
How to evaluate the relevance of a search made with an AI Agent?
Awarded Jun 6 at 8:47
Pytorch Encoder not working [closed]
Awarded Jun 4 at 6:36
The format of data for text generation using LLM
Awarded Jun 2 at 22:13
Is sparsity required for behaviour exhibited by modular neural networks such as compositional generalisation, resiliency to catastrophic learning?
Awarded May 31 at 18:51
Why are the Q and K matrices two separate matrices in attention?
Awarded May 27 at 15:56
Are there problems where the optimal policy is stochastic?
Awarded May 27 at 12:18
tic-tac-toe - tabular q-learning - what is the formula to calculate the number of entries in the q-table
Awarded May 22 at 21:10
Which is the probability of JohnCalls given Burglary? Why?
Awarded May 17 at 11:11
When to use Tanh?
Awarded May 16 at 1:27
Reference request: data efficiency of LLM pre-training
Awarded May 15 at 18:48
What should be Relationship between embedding dimension and context length?
Awarded May 15 at 7:30
Neural network for specific numbers from a range (Q learning)
Awarded May 11 at 4:10
1
2 3 4 5
…
45