OmG's user avatar
OmG's user avatar
OmG's user avatar
OmG
  • Member for 5 years, 9 months
  • Last seen this week
5 votes
Accepted

What does "semantic gap" mean?

4 votes
Accepted

What is numerical stability?

4 votes

Can prior knowledge be encoded in deep neural networks?

3 votes
Accepted

How can active learning be used in the case of complex models that require a lot of data?

3 votes

What's going on in the equation of the variational lower bound?

3 votes
Accepted

How does the Kullback-Leibler divergence give "knowledge gained"?

3 votes
Accepted

How does size of the dataset depend on VC dimension of the hypothesis class?

3 votes
Accepted

What is the difference between hill-climbing and greedy best-first search algorithms?

3 votes
Accepted

Why are Siamese Neural Networks used instead of a single neural network?

3 votes

Does elitism cause premature convergence in genetic algorithms?

3 votes

What are the main ideas behind NER?

3 votes
Accepted

Any comparison between transformer and RNN+Attention on the same dataset?

2 votes
Accepted

Is the VC Dimension meaningful in the context of Reinforcement Learning?

2 votes

Which metric should I use to assess the quality of the clusters?

2 votes

What's the threshold to call something 'machine learning'?

2 votes
Accepted

What does "Gau" in GauGAN stand for?

2 votes
Accepted

What are the typical sizes of practical/commercial artificial neural networks?

2 votes

Can Reinforcement Learning be used to generate sequences?

2 votes

Is knowing underlying probability distribution mandatory for deciding iid property of random variables?

2 votes

Are there deep networks that can differentiate object class from individual object?

2 votes
Accepted

Understanding relation between VC Symmetrization Lemma and Generalization Bounds

2 votes

What kind of problems cannot be solved using machine learning techniques?

2 votes

Why does estimation error increase with $|H|$ and decrease with $m$ in PAC learning?

2 votes
Accepted

How do I prove that $\mathcal{H}$, with $\mathcal{VC}$ dimension $d$, shatters all subsets with size less than $d-1$?

2 votes
Accepted

What does the notation ${s'\sim T(s,a,\cdot)}$ mean?

2 votes

What is the name of an AI system that learns by trial and error?

2 votes

Why does the hill climbing algorithm only produce a local maximum?

2 votes

Why does Google Translate produce two different translations for the same Chinese text?

2 votes
Accepted

What is the difference between meta-learning and zero-shot learning?

2 votes
Accepted

Do I need an encoder-decoder architecture to predict the next item of a sequence?