Artificial Intelligence Stack Exchange

4 votes

1 answer

3k views

What are the major differences between cost, loss, error, fitness, utility, objective, criterion functions?

nbro

43.1k

modified 1 hour ago

3 votes

1 answer

1k views

How to identify the geometry (vertices and edges) of objects in images?

nbro

43.1k

modified 2 hours ago

2 votes

0 answers

18 views

Identifying and Reducing Persistent Artifacts in Neural Vocoders

nbro

43.1k

modified 2 hours ago

4 votes

2 answers

755 views

Why is Batch Gradient Descent performing worse than Stochastic and Mini-Batch Gradient Descent?

Mithical♦

2,984

modified 3 hours ago

0 votes

0 answers

48 views

How to avoid bias with administrative censoring in survival models

CommunityBot

1

modified 3 hours ago

2 votes

3 answers

2k views

Why do LLMs need massive distributed training across nodes -- if the models fit in one GPU while batch decreases the variance of gradients?

profPlum

566

answered 9 hours ago

3 votes

2 answers

879 views

Is $(y_i - \hat y_i)x_i$, part of the formula for updating weights for perceptron, the gradient of some kind of loss function?

CommunityBot

1

modified 21 hours ago

2 votes

3 answers

97 views

How to make AI reliably use uploaded documentation without hallucinating?

Tayyaba Ameen

1

answered 2 days ago

5 votes

1 answer

482 views

NEAT can't solve XOR completely

CommunityBot

1

modified Nov 23 at 2:07

1 vote

1 answer

184 views

Since ReLU activations also result in a sparse network, does it have the same "feature selection" property as L1 regularization?

CommunityBot

1

modified Nov 22 at 23:03

1 vote

1 answer

173 views

What does "All store and access operations (for S(t) , A(t), and R(t)) can take their index mod n + 1" mean?

CommunityBot

1

modified Nov 22 at 7:06

1 vote

2 answers

314 views

What kind of algorithm or approach can I use to find a specific type of object in an image?

CommunityBot

1

modified Nov 22 at 4:11

3 votes

1 answer

340 views

Why do I get small probabilities when implementing a multinomial naive Bayes text classification model?

CommunityBot

1

modified Nov 21 at 9:05

0 votes

1 answer

102 views

I'm trying to train an AI but I have low accuracy using rust and pytorch

CommunityBot

1

modified Nov 20 at 17:03

Stack Exchange Network

Explore our questions

What are the major differences between cost, loss, error, fitness, utility, objective, criterion functions?

How to identify the geometry (vertices and edges) of objects in images?

Identifying and Reducing Persistent Artifacts in Neural Vocoders

Why is Batch Gradient Descent performing worse than Stochastic and Mini-Batch Gradient Descent?

How to avoid bias with administrative censoring in survival models

Why do LLMs need massive distributed training across nodes -- if the models fit in one GPU while batch decreases the variance of gradients?

Is $(y_i - \hat y_i)x_i$, part of the formula for updating weights for perceptron, the gradient of some kind of loss function?

How to make AI reliably use uploaded documentation without hallucinating?

NEAT can't solve XOR completely

Since ReLU activations also result in a sparse network, does it have the same "feature selection" property as L1 regularization?

What does "All store and access operations (for S(t) , A(t), and R(t)) can take their index mod n + 1" mean?

What kind of algorithm or approach can I use to find a specific type of object in an image?

Why do I get small probabilities when implementing a multinomial naive Bayes text classification model?

I'm trying to train an AI but I have low accuracy using rust and pytorch

Hot Network Questions