Highest Voted 'learning-curve' Questions - Artificial Intelligence Stack Exchange

4

votes

0 answers

Is there a mathematical formula that describes the learning curve in neural networks?

In training a neural network, you often see the curve showing how fast the neural network is getting better. It usually grows very fast then slows down to almost horizontal. Is there a mathematical formula that matches these curves? Some similar…

asked Jan 09 '20 at 14:55

zooby

2,196
1
11
21

3

votes

0 answers

How to interpret the training loss curves in Soft-Actor-Critic (SAC)?

I am using stable-baseline3 implementation of the Soft-Actor-Critic (SAC) algorithm. The plotted training curves look promising. However, I am not fully sure how to interpret the actor and critic losses. The entropy coefficient $\alpha$ is…

deep-rl actor-critic-methods loss soft-actor-critic learning-curve

asked Jul 01 '21 at 07:44

Manuel

45
5

2

votes

1 answer

Spikes in of Train and Test error

I learn a DNN for image recognition. During each epoch, I calculate mean loss in the training set. After each epoch, I calculate loss and number of errors over both training and test set. The problem is, training and test error go to (almost) zero,…

deep-learning deep-neural-networks learning-curve

asked Jul 16 '19 at 08:23

user31264

203
1
8

1

vote

0 answers

Bias-variance tradeoff and learning curves for non-deep learning models

I am following a course on machine learning and am confused about the bias-variance trade-off relationship to learning curves in classification. I am seeing some conflicting information online on this. The scikit-learn learning curve looks like the…

bias-variance-tradeoff learning-curve

asked Nov 12 '20 at 11:14

ML-Student-1996

11
2

1

vote

1 answer

LSTM text classifier shows unexpected cyclical pattern in loss

I'm training a text classifier in PyTorch and I'm experiencing an unexplainable cyclical pattern in the loss curve. The loss drops drastically at the beginning of each epoch and then starts rising slowly. However, the global convergence pattern…

long-short-term-memory objective-functions pytorch learning-curve

asked Jul 26 '19 at 12:39

David

511
3
12

0

votes

1 answer

How to explain that a same DNN model have radically different behaviours with each new initialization and training?

I'm trying to predict the continuous values of a variable $y$ using a Fully Connected Neural Network while providing it with data from a $(3300, 13)$ matrix $X$ where $X[i, :]=[0,...,1,...,0,x_{i}]$. So the first $12$ elements of a data vector are…

regression relu weights-initialization dense-layers learning-curve

asked Apr 14 '21 at 02:20

Daviiid

563
3
15

Questions tagged [learning-curve]

Is there a mathematical formula that describes the learning curve in neural networks?

How to interpret the training loss curves in Soft-Actor-Critic (SAC)?

Spikes in of Train and Test error

Bias-variance tradeoff and learning curves for non-deep learning models

LSTM text classifier shows unexpected cyclical pattern in loss

How to explain that a same DNN model have radically different behaviours with each new initialization and training?