'transformer' New Answers

0

What does it mean to apply decomposition at inference-time in a machine translation system?

I've found this article that seems to answer my question: https://hazelcast.com/glossary/machine-learning-inference/ From this, my understanding is that inference-time describes when a machine learning system is put into use following training; so basically at the time of task application. I think this would mean that the paper's authors are stating that the ...

answered 19 hours ago

ticiarai

11 bronze badge

0

Is PositionalEncoding needed for using Transformer models correctly?

Positional Encodings in Transformers exist to give the model some information about the position of the embedding. This makes sense in fields like NLP or Time Series Data, since the position(order) matters in this case. However, since you say that order of the data is not relevant in your use case, positional encoding would not be necessary.

deep-learning natural-language-processing transformer

answered Nov 17 at 1:35

DKDK

1264 bronze badges

2

Why do language models produce different outputs for same prompt?

Language models produce a probability distribution over a set of words. You determine the next word by sampling from this distribution. So, determining the next word is stochastic even though the distribution is the same given the initial prompt.

deep-learning transformer language-model natural-language-generation forward-pass

answered Nov 12 at 23:15

SpiderRico

7723 silver badges12 bronze badges

0

What is input (and shape) to K/V/Q of self-attention of EACH Decoder block of Language-translation model Transformer's tokens during Inference?

Edit 3 OP seems to think value, query and keys are supposed to be different in the original Vaswani multi-head attention. As can be seen in Keras' documentation on their implementation of the multi-headed attention layer, "If query, key, value are the same, then this is self-attention." Edit 2 One thing missing from the graphics you use are the ...

transformer attention machine-translation language-model encoder-decoder

answered Nov 9 at 16:02

Avatrin

3561 silver badge6 bronze badges

1

Do Vision Transformers handle arbitrary sequence lengths the same way as normal Transformers?

Yes, they can handle sequences with arbitrary length sequence, but with some remarks. In the paper Training data-efficient image transformers & distillation through attention authors train models in the resolution 224x224 (1 + 14x14 tokens) and then finetune to the 384x384 (1 + 28x28 tokens). Weights to produce queries, keys, values, as well as ...

neural-networks computer-vision transformer vision-transformer

answered Nov 4 at 6:49

spiridon_the_sun_rotator

1,3692 silver badges9 bronze badges

0

Is there a notion of location in Transformer architecture in subsequent self-attention layers?

Attention mechanism solves this problem by allowing the decoder to “look-back” at the encoder's hidden states based on its current state. This allows the decoder to extract only relevant information about the input tokens at each decoding, thus learning more complicated dependencies between the input and the output.

transformer attention positional-encoding

answered Oct 31 at 11:31

robert4johnson

1

Stack Exchange Network

current community

your communities

more stack exchange communities

Tag Info

New answers tagged transformer