Artificial Intelligence

Teacher

 Teacher
Answer a question with score of 1 or more.
Awarded 2381 times.
How can I teach a book to an LLM?
Awarded 21 hours ago
Does a decoder in transformer model generate output embeddings like the following?
Awarded yesterday
Is it possible that Precision and Recall increase together?
Awarded Nov 27 at 10:10
is there a mathematical explanation of precision and recall tradeoff?
Awarded Nov 25 at 1:06
Is it possible to do machine learning on encrypted images?
Awarded Nov 23 at 18:26
how to determine the number of units for dense layer for transfer learning?
Awarded Nov 22 at 1:48
In a DDQN architecture, why is the value of a state assumed to be the average of the Q values of the actions?
Awarded Nov 20 at 7:58
What causes my loss curve to consistently oscillate when training an LLM?
Awarded Nov 18 at 17:06
How much energy consumption is involved in Chat GPT responses being generated?
Awarded Nov 16 at 6:43
How much energy consumption is involved in Chat GPT responses being generated?
Awarded Nov 16 at 6:43
My model is only improving when learning rate is 1. Should I be worried?
Awarded Nov 16 at 0:52
Why is it called multi-headed attention?
Awarded Nov 15 at 8:11
Is a VGG-based CNN model sometimes better for image classfication than a modern architecture?
Awarded Nov 11 at 4:10
Monte Carlo Tree Search for trick taking games, such as Whist, Bridge
Awarded Nov 10 at 10:34
Does it make sense to apply batch normalization to a batch size of 1?
Awarded Nov 6 at 7:51
Can multiple linear regression using the least squares(OLS) method, also be used to solve simple linear regression problems? Would both be equivalent?
Awarded Nov 5 at 17:34
For an LLM model, how can I estimate its memory requirements based on storage usage?
Awarded Nov 5 at 17:20
Why is search important in AI?
Awarded Nov 4 at 9:03
time-series prediction : loss going down, then stagnates with very high variance
Awarded Nov 2 at 8:34
Super Resolution CNN generates black dots on output images
Awarded Oct 30 at 2:22
How can abstract graphs be recognized by neural nets?
Awarded Oct 29 at 11:28
ML predicting output based on single feature
Awarded Oct 29 at 0:37
What is Explainable AI and what does it strive for?
Awarded Oct 28 at 0:37
Why do ChatGPT “jailbreaks” work?
Awarded Oct 26 at 10:55
Defining formula for fuzzy equation
Awarded Oct 25 at 23:55
Why do ChatGPT “jailbreaks” work?
Awarded Oct 25 at 17:49
How to extract the high-level features of YOLOv5?
Awarded Oct 24 at 9:27
LLM-like architecture capable of dynamically learning from its own output
Awarded Oct 24 at 0:32
LLM-like architecture capable of dynamically learning from its own output
Awarded Oct 24 at 0:32
Can an RNN predict a sinus curve with no input?
Awarded Oct 23 at 0:56
Back-of-the-envelope machine learning (specifically neural networks) calculations
Awarded Oct 21 at 1:56
How does ChatGPT respond to novel prompts and commands?
Awarded Oct 21 at 1:56
How does ChatGPT respond to novel prompts and commands?
Awarded Oct 21 at 1:56
Reasoning behind performance improvement with hopfield networks
Awarded Oct 21 at 1:56
Can the multiclass classification be modified to binary classification for better accuracy
Awarded Oct 21 at 1:48
How can I use Artificial Intelligence to compare to paragraphs to see if they share the same meaning?
Awarded Oct 20 at 7:01
While fine-tuning a decoder only LLM like LLaMA on chat dataset, what kind of padding should one use?
Awarded Oct 17 at 18:41
How do Multimodal LLMs of 2023 score on the ARC benchmark (in 2020: 20% Accuracy)
Awarded Oct 16 at 10:43
Modifying the population neurons at runtime - Framework and resources
Awarded Oct 15 at 0:42
MCTS: Units away from the action
Awarded Oct 11 at 8:34
Realizability Assumption: Why is that for every ERM hypothesis $L_{S}(h_{S})=0$
Awarded Oct 11 at 2:06
Is model order of a model class (for example, polynomial regression class) a hyperparameter or a tuning parameter?
Awarded Oct 9 at 17:25
Why any set of m data points with different features can be perfectly fit by a polynomial of degree n as long as n ≥ m
Awarded Oct 7 at 3:22
Surveys/Important papers in Explainability for LLM?
Awarded Oct 5 at 12:10
How to filter out class for which the model has not been trained in ml web app?
Awarded Oct 4 at 20:51
What is $D_i$ in "Common Principal Components Analysis"?
Awarded Oct 3 at 21:56
Why does the activation function for a hidden layer in a MLP have to be non-polynomial?
Awarded Oct 3 at 7:27
Approximate the chance of a number is prime using neural network
Awarded Oct 2 at 10:26
Has anyone tried to use llama.cpp with NVLink?
Awarded Sep 30 at 3:04
Gradient: any resource on how to understand everything about it?
Awarded Sep 30 at 0:27
How does Alpha Go Zero MCTS work in parallel?
Awarded Sep 27 at 0:41
What is the best lightweight alternative to VGG16 for image fingerprinting?
Awarded Sep 26 at 15:36
Can some one help me understand this paragraph from Nvidia's progressive GAN paper?
Awarded Sep 23 at 21:04
Calculating mutual information between layer outputs and targets in a neural network
Awarded Sep 22 at 13:55
How to prompt Open AI for a variable list length?
Awarded Sep 19 at 16:11
Why Does the Model not Improve in PyTorch?
Awarded Sep 18 at 5:58
Why do the values in the cross attentional mechanism within a transformer come from the encoder and not from the decoder?
Awarded Sep 16 at 21:52
Feeding YOLOv4 image data into LSTM layer?
Awarded Sep 15 at 17:25
$\gamma^t$ in REINFORCE update (Sutton-Barto RL book Exercise 13.2)
Awarded Sep 11 at 18:56
Is it possible to reconstruct convolutional layers' input using transposed convolution?
Awarded Sep 10 at 3:17
1
2 3 4 5
…
40

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.