mirror2image's user avatar
mirror2image's user avatar
mirror2image's user avatar
mirror2image
  • Member for 3 years, 7 months
  • Last seen more than 1 year ago
9 votes
Accepted

Do we have to use CNN for Deep Q Learning?

3 votes
Accepted

How to chose dense layer size?

3 votes

How do I improve accuracy and know when to stop training?

3 votes

What sort of mathematical problems are there in AI that people are working on?

3 votes
Accepted

Is it possible with stochastic gradient descent for the error to increase?

2 votes

Combining deep reinforcement learning with alpha-beta pruning

2 votes

How do we design a neural network such that the $L_1$ norm of the outputs is less than or equal to 1?

2 votes

Wouldn't convolutional neural network models work better without flattening the input in any stages?

2 votes

Why do self-driving cars use a radar?

2 votes
Accepted

Can DQN perform better than Double DQN?

2 votes

Why are the initial weights of neural networks randomly initialised?

1 vote

How to stop DQN Q function from increasing during learning?

1 vote

How can we reach global optimum?

1 vote

How do the achievements met in the gaming field (ex. AlphaGo Zero) impact other fields of application?

1 vote

How do I detect similar objects in an image?

1 vote

IQN bellman target: using Z vs using Q

1 vote

Tips for keeping the distribution of weights normal

1 vote

In DQN, updating target network every N steps or slowly update every step is better?

1 vote

What is the difference between DQN and AlphaGo Zero?

1 vote

Is there an alternative to the use of target network?

1 vote

Multicamera Tracking vs Single Fisheye Camera

1 vote

In this implementation of the Information Set Monte Carlo Tree Search, why can't the players see the cards of each other?

1 vote

Is it ok to struggle with mathematics while learning AI as a beginner?

1 vote

Is there a limit of minimum error for a particular training dataset in artificial Neural Network?

1 vote

what are the similarity measure use for both continuous and categorical data?

1 vote
Accepted

If I use MobileNetV2 for the encoder, can I use a different architecture for the decoder?

0 votes

Why don't people use projected Bellman error with deep neural networks?

0 votes

How does the regression layer in the localization network of a spatial transformer work?

0 votes

Can bounding boxes further improve the performance of a CNN classifier?

0 votes

How to identify too small network in reinforcement learning?