SpiderRico's user avatar
SpiderRico's user avatar
SpiderRico's user avatar
SpiderRico
  • Member for 2 years, 8 months
  • Last seen this week
3 votes

If features are always positives, why do we use RELU activation functions?

2 votes
Accepted

Why is the validation performance better than the training performance?

2 votes

When using PCA for dimensionality reduction of the feature vectors to speed up learning, how do I know that I'm not letting the model overfit?

2 votes

Why do language models produce different outputs for same prompt?

2 votes

What does it mean when accuracy of regularized model is higher for training set than for validation set?

1 vote

How to make an output independent of input feature in neural networks?

1 vote

Are there any decentralized examples of AI systems with blockchain technology?

1 vote

Test accuracy decreases during my train process

1 vote

What are examples of good free books that cover the back-propagation algorithm?

1 vote
Accepted

How would the performance of federated learning compare to the performance of centralized machine learning when the data is i.i.d.?

1 vote

Is a basic neural network architecture better with small datasets?

1 vote
Accepted

What type of ANN architecture to choose?

1 vote

Which class of functions are quite complicated in deep learning?

1 vote

Why data required for hyperparameter tuning is considered as an additional data?

1 vote
Accepted

How to prove that gradient descent doesn't necessarily find the global optimum?

1 vote

What is the simplest classification problem which cannot be solved by a perceptron?

1 vote
Accepted

Where is L2-regularization term applied

1 vote
Accepted

Which one is more important in case of different loss optimization algorithms, Speed or the Route?

0 votes

Can cryptocurrency charts be estimated using neural networks?

0 votes

Why the cost/loss starts to increase for some iterations during the training phase?

0 votes

How can I incrementally train a Yolo model without catastrophic forgetting?

0 votes

Is pruning only applicable to convolutional neural networks?

0 votes

When exactly am I overfitting -- contradicting metrics

0 votes

Handling imbalanced data with multiple targets

0 votes

Are derived or computed inputs bad for CNNs?

0 votes

Are these book example CNN results realistic?