Djib2011's user avatar
Djib2011's user avatar
Djib2011's user avatar
Djib2011
  • Member for 3 years, 3 months
  • Last seen more than a week ago
75 votes
Accepted

Why do we need explainable AI?

52 votes
Accepted

How could artificial intelligence harm us?

22 votes

Are neural networks prone to catastrophic forgetting?

11 votes

Is there a way to understand neural networks without using the concept of brain?

9 votes
Accepted

What is the meaning of $V(D,G)$ in the GAN objective function?

6 votes

What do the words "coarse" and "fine" mean in the context of computer vision?

5 votes
Accepted

What is the best measure for detecting overfitting?

5 votes
Accepted

Can we optimize an optimization algorithm?

5 votes
Accepted

Are deep learning models more prone to overfitting than machine learning ones?

5 votes

What is the purpose of the batch size in neural networks?

5 votes
Accepted

What is the “Hello World” problem of Unsupervised Learning?

4 votes

How should I deal with variable-length inputs for neural networks?

4 votes

Are there any better visual models for transfer rather than ImageNet?

3 votes
Accepted

Are feature maps merged or are they passed on as they are?

3 votes
Accepted

Is unsupervised learning a branch of AI?

3 votes
Accepted

Can neurons in MLP and filters in CNN be compared?

3 votes

How does the neural-network know how to tweak weights for a specific neuron?

3 votes
Accepted

How does the generator in GAN's work?

3 votes

How many layers exists in my neural network?

3 votes

What is the difference between model and data distributions?

3 votes
Accepted

Can TensorFlow, PyTorch, and other mainstream ML frameworks be used for research-grade work in AI?

3 votes

What is the use of the regular convolutional layer in expansion path of U-Net?

2 votes

What is eager learning and lazy learning?

2 votes

What does end-to-end training mean?

2 votes
Accepted

What are the features get from a feature extraction using a CNN?

2 votes

Turn photos right-side up?

2 votes

Is there any difference between the convolution operation applied to images and applied to other numerical 2D data?

2 votes
Accepted

Are the training loss and validation loss plotted per sample or per batch?

2 votes
Accepted

Query regarding the minmax loss function formulation of the training of a Generative Adversarial Network (GAN)

2 votes
Accepted

How are exploding numbers in a forward pass of a CNN combated?