Artificial Intelligence Stack Exchange Community Digest

Top new questions this week:

Doesn't every single machine learning classifier use conditional probability/Bayes in its underlying assumptions?

I’m reading about how Conditional Probability/ Bayes Theorem is used in Naive Bayes in Intro to Statistical Learning, but it seems like it isn’t that “groundbreaking” as it is described? If …

machine-learning classification naive-bayes bayes-theorem conditional-probability

asked by Katsu Score of 3 answered by Dr. Snoopy Score of 3

How much of the ChatGPT output is copied from its training set (vs. being abstractively generated)?

One of the main concerns of using ChatGPT answers on Stack Exchange is that it may copy verbatim or almost verbatim some text from its training set, which may infringe the source text’s license. This …

text-generation chat-gpt

asked by Franck Dernoncourt Score of 3

Which correlated feature should be eliminated from a model?

BACKGROUND: There is a lot of information online about the problem of multicollinearity as it relates to machine learning and how to identify correlated features. However, I am still unclear on which …

machine-learning feature-selection multicollinearity

asked by Snehal Patel Score of 2 answered by oseekero Score of 1

Is there any interpretation method suitable for CNNs which do regression tasks?

I mainly tackle regression problems by CNNs, and want to find a reliable method to calculate the heatmaps for NN’s results. However, I find almost all interpretation methods including CAM is used for …

convolutional-neural-networks regression algorithm-request model-request explainable-ai

asked by minghuisvn Score of 2 answered by Dr. Snoopy Score of 0

Why use z_mean to plot the latent space learned by a Variational Autoencoder?

In the Keras website, there is an example code of a Variational Autoencoder. At the end of such a page, there is an example code that plots the latent space learned from MNIST. The code is as follows: …

keras variational-autoencoder

asked by AlexSC Score of 2

Could one still learn a good policy by doing a backprop every fixed number of steps within an episode?

Waiting an entire episode before doing a backprop can build up a very large computational graph, which is a burden on memory. Could one still learn a good policy by doing a backprop every fixed number …

reinforcement-learning reference-request policy-gradients

asked by Archie Gertsman Score of 1 answered by Hadar Sharvit Score of 1

Can the truth value of unobserved sentences be computed from known sentences only?

Truthfulness is a quality that Sam Altman mentioned to be improvable on ChatGPT. This question considers a small example to try to understand the problem. A large language model includes a large set …

logic chat-gpt truth

asked by Jaume Oliver Lafont Score of 1 answered by mohottnad Score of 1

Greatest hits from previous weeks:

How do I compute the structural similarity between sentences?

I am working on a problem where I need to determine whether two sentences are similar or not. I implemented a solution using BM25 algorithm and wordnet synsets for determining syntactic & …

natural-language-processing python similarity

asked by Shubham Tiwari Score of 13 answered by Oliver Mason Score of 2

How should I handle invalid actions (when using REINFORCE)?

I want to create an AI which can play five-in-a-row/Gomoku. I want to use reinforcement learning for this. I use the policy gradient method, namely REINFORCE, with baseline. For the value and policy …

reinforcement-learning policy-gradients actor-critic-methods reinforce reward-design

asked by Molnár István Score of 39 answered by BlindKungFuMaster Score of 21

What is the difference between a convolutional neural network and a regular neural network?

I’ve seen these terms thrown around this site a lot, specifically in the tags convolutional-neural-networks and neural-networks. I know that a neural network is a system based loosely on the human …

neural-networks convolutional-neural-networks comparison terminology definitions

asked by Mithical Score of 39 answered by Borhan Kazimipour Score of 40

How can we process the data from both the true distribution and the generator?

I’m struggling to understand the GAN loss function as provided in Understanding Generative Adversarial Networks (a blog post written by Daniel Seita). In the standard cross-entropy loss, we have an …

neural-networks deep-learning objective-functions generative-adversarial-networks generative-model

asked by tryingtolearn Score of 20 answered by Douglas Daseeco Score of 7

What are the advantages of ReLU vs Leaky ReLU and Parametric ReLU (if any)?

I think that the advantage of using Leaky ReLU instead of ReLU is that in this way we cannot have vanishing gradient. Parametric ReLU has the same advantage with the only difference that the slope of …

neural-networks activation-functions relu

asked by gvgramazio Score of 19 answered by Douglas Daseeco Score of 13

How do I show that uniform-cost search is a special case of A*?

How do I show that uniform-cost search is a special case of A*? How do I prove this?

comparison search proofs a-star uniform-cost-search

asked by dua fatima Score of 5 answered by nbro Score of 7

1 hidden layer with 1000 neurons vs. 10 hidden layers with 100 neurons

These types of questions may be problem-dependent, but I have tried to find research that addresses the question whether the number of hidden layers and their size (number of neurons in each layer) …

neural-networks

asked by Stephen Johnson Score of 16 answered by Thomas Wagenaar Score of 13