Skip to main content
Luca Anzalone's user avatar
Luca Anzalone's user avatar
Luca Anzalone's user avatar
Luca Anzalone
  • Member for 1 year, 3 months
  • Last seen this week
12 votes

What is the difference between self-supervised and unsupervised learning?

8 votes

Can you confirm that the transformer works strictly deterministically and there is no randomness inside or between the attention layers?

7 votes
Accepted

Does increasing the number of Q functions in Q-Learning scale?

6 votes
Accepted

What is curriculum learning in reinforcement learning?

4 votes

How does gradient descent work with relu if weights are negative?

4 votes
Accepted

Deep Q Networks v Monte Carlo Tree Search in Alpha Zero

4 votes
Accepted

Why use ReLU over Leaky ReLU?

4 votes

Why can we have misclassifications for a perfect model in logistic regression?

4 votes
Accepted

What are reward networks in reinforcement learning?

3 votes

Would a pipeline of different models be considered Ensemble Learning?

3 votes
Accepted

DQN arXiv 10-year anniversary: What are the outstanding problems being actively researched in deep Q-learning since 2019?

3 votes
Accepted

Selection of actions based on distribution of rewards

3 votes
Accepted

How does one normalize observations in online reinforcement learning

3 votes

Comparison of the two alternative forms for the KL divergence

3 votes
Accepted

What is the impact of the initialization of weights in the performance of a neural network in machine learning?

3 votes

Definition of negatives in NT-Xent loss

3 votes

Is evolutionary algorithm dead as same as symbolic AI?

3 votes

Should I use pretrained model for image classification or not?

3 votes

Can I speed up NN training by manually guiding training?

3 votes
Accepted

Do different models using early stopping have the same validation set to check model training performance?

3 votes

How does deep learning overcome overfitting?

2 votes
Accepted

How does a Machine Learning model predict this classification problem?

2 votes
Accepted

How do policy gradients work?

2 votes

How can I make an MNIST digit recognizer that rejects out-of-distribution data?

2 votes

Target Network inversed in Deep Q Learning (Reinforcement Learning)

2 votes
Accepted

Fluctuations in loss during in epoch evaluation of GRU

2 votes

Why does Batch-Normalization before ReLU work?

2 votes
Accepted

What is the basic difference between NAS, Hyperparameter Optimization/Tuning and Pruning?

2 votes

How do I assign a weight to an additional loss?

2 votes

How to apply backpropagation when one layer of the network is a call-only function (no gradient)?