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

0 votes
0 answers
15 views

Prefix tuning in LLM uses learnable vectors to fine tune the model

1 vote
1 answer
65 views

How does a multidimensional vector get fed into a single node in a neural network?

1 vote
3 answers
62 views

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

2 votes
1 answer
141 views

How would the probability of a document $P(d)$ be computed in the Naive Bayes classifier?

0 votes
2 answers
679 views

Does it make sense to add an additional attention layer while fine-tuning Bert?

1 vote
1 answer
45 views

NLP "small" model to improve "big" model

7 votes
2 answers
5k views

How to resolve lexical ambiguity in natural language processing?

1 vote
1 answer
87 views

Masking in Decoder of Transformer

1 vote
0 answers
19 views

What is the input to an encoder-decoder transformer in next word prediction task?

0 votes
1 answer
34 views

Setting number of rows returned by vector stores

2 votes
2 answers
1k views

How does a LLM (transformer) pick words from its vocabulary?

2 votes
2 answers
291 views

How do LSTM and GRU avoid to overcome the vanishing gradient problem?

2 votes
1 answer
976 views

If GPT-3 is trained on predicting the next token, how is it able to take commands?

6 votes
2 answers
391 views

How does GPT-based language model like ChatGPT determine the n-th letter of a word?

Browse more Questions