Skip to main content
Share Your Experience: Take the 2024 Developer Survey
user10296606's user avatar
user10296606's user avatar
user10296606's user avatar
user10296606
  • Member for 5 years, 8 months
  • Last seen more than a month ago
  • Canada
35 votes
4 answers
80k views

How to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?

30 votes
4 answers
59k views

macro average and weighted average meaning in classification_report

10 votes
1 answer
16k views

How do GBM algorithms handle missing data?

10 votes
2 answers
18k views

what is difference between the DDQN and DQN?

9 votes
1 answer
13k views

clipping the reward for adam optimizer in keras

7 votes
1 answer
4k views

What are the effects of clipping the reward in stability?

6 votes
3 answers
1k views

What is the best metric to evaluate highly imbalanaced binary classifiction? (such as fraud detection in credit card)

6 votes
2 answers
2k views

How to choose between discounted reward and average reward?

6 votes
2 answers
8k views

Is NN with no hidden layer is behave like a regression?

5 votes
1 answer
10k views

What is the relationship between MDP and RL?

4 votes
1 answer
648 views

How to implement clipping the reward in DQN in keras

4 votes
1 answer
1k views

Why does exploration in DQN not lead to instability?

4 votes
1 answer
3k views

What is the difference between dynamic programming and Q-learning?

4 votes
2 answers
402 views

If in t-SNE digaram of binary classification both classes follow the similar curve what does t-SNE diagram show?

3 votes
1 answer
50 views

When unsupervised learning is more beneficial in comparison with supervised learning even the labelings are existed?

3 votes
1 answer
468 views

How to use a different model to deep neural network with reinforcement learning based on DQN?

3 votes
1 answer
94 views

How to test unsupervised learning methods for anomaly detection?

2 votes
0 answers
92 views

How to tune the hyperparameters of XGBoost and RF? [closed]

2 votes
1 answer
632 views

Is the neural network in DQN used to learn like a supervised model?

2 votes
1 answer
135 views

How we can have RF-QLearning or SVR-QLearning (Combine these algorithm with a Q-Learning )

2 votes
0 answers
221 views

How to resolve the instability of average reward per episode in training of DQN (Deep Q-Network)?

2 votes
3 answers
330 views

Which is more important - stable training results or good test results?

2 votes
1 answer
66 views

"Each agent was evaluated every 250,000 training frames for 135,000 validation frames" What does this sentences stands for? in DQN nature paper?

2 votes
2 answers
2k views

What are the differences between Reinforcement Learning (RL) and Supervised Learning?

2 votes
2 answers
535 views

how to see decision tree when running in anaconda?

1 vote
1 answer
2k views

comparison of t-SNE and PCA and truncate SVD

1 vote
2 answers
119 views

unsupervised anomaly detection for univariate fast frequency time series data?

1 vote
0 answers
37 views

What is the meaning of the Variant Q-learning and To what INPUT and OUTPUT refer? in Abstract of DeepMind DQN paper 2013

1 vote
2 answers
510 views

What is meaning of zip(kfold.split(X, Y) in sklearn

1 vote
1 answer
451 views

What is difference between final episodes of training and test in DQN?