Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community
Anybody can ask a question
Anybody can answer
The best answers are voted up and rise to the top

Explore our Questions

3 votes
1 answer
190 views
What is a simplified way to explain why the AI researchers Bengio, Hinton, and Lecun, won the 2018 Turing Award?
0 votes
0 answers
20 views
NLP disambiguation from multiple choice without embedding, supervised
0 votes
0 answers
10 views
Does Grad-CAM/saliency maps work properly with a model using dropout and batch normalization?
1 vote
2 answers
142 views
How can the input order of pairs into a neural network not matter (i.e. symmetry)?
1 vote
1 answer
39 views
Reinforcement Learning applied to Optimisation Problem
0 votes
0 answers
17 views
LSTM performance strictly decreases with sequence length input
0 votes
1 answer
30 views
What techniques exist to increase the learning importance of difficult-to-learn labels over easy ones?
0 votes
1 answer
42 views
How should I initialize the weights of the neural network so that the initial policy is uniform?
0 votes
2 answers
45 views
How much labelling is required for NER with SpaCy?
0 votes
0 answers
23 views
Test accuracy go down after decreasing learning rate
0 votes
1 answer
40 views
Is learning rate the only reason for training loss oscillation after few epochs?
1 vote
1 answer
42 views
Triplet Loss- Three forward pass and one backward pass(Propagation)
-1 votes
1 answer
31 views
Are any non-injective activation functions used?
1 vote
1 answer
36 views
Why doesn't dropout mislead results during evaluation?
Browse more Questions