Skip to main content
DrMcCleod's user avatar
DrMcCleod's user avatar
DrMcCleod's user avatar
DrMcCleod
  • Member for 6 years, 4 months
  • Last seen more than a month ago
8 votes
Accepted

Why can a fully convolutional network accept images of any size?

6 votes
Accepted

How can I apply reinforcement learning to solve this asteroid game?

4 votes
Accepted

Understanding the configuration of replay memory and epsilon in deep reinforcement learning

2 votes

Finding anomaly detection by pattern matching in a set of continous data

2 votes
Accepted

What are criteria for ML model to be satisfactory for commercial use?

2 votes

Evolving Machine Learning

2 votes

In Q-learning, wouldn't it be better to simply iterate through all possible states?

1 vote

Are there any pathfinding algorithms that take customized rules into account when determining the shortest path?

1 vote

What is the difference between encoders and auto-encoders?

1 vote

How TensorFlow will know if the prediction is true or false?

1 vote

Can I filter barking sounds on the television?

1 vote
Accepted

Beginner - Object classification data in a neural network

1 vote

Deep Q-learning is not performing well when there are several enemies

1 vote

What are examples of applications of the Fourier transform to AI?

1 vote

How do we define the reward function for an environment?

0 votes

Would it be ethical to use AI to determine a user’s gender from the content they upload, without them knowing?

0 votes

Is it possible for a neural network to be used to compress data?

0 votes
Accepted

Couldn't an AI cheat when trying to follow its goal?

0 votes

Preventing bias by not providing irrelevant data

0 votes

When are Q values calculated in experience replay?

0 votes

Is it possible for a NN to reach the same results as CNNs?

0 votes

Can some one help me understand this paragraph from Nvidia's progressive GAN paper?

0 votes
Accepted

In the graph search version of A*, can I stop the search the first time I encounter the goal node?

0 votes

Why do very deep non resnet architectures perform worse compared to shallower ones for the same iteration? Shouldn't they just train slower?

-1 votes

Can we implement GAN (Generative adversarial neural networks) for classication problem like Fraud detecion?