Latest Exam Prep

QUESTION 23
In the transformer architecture, what is the purpose of positional encoding?

QUESTION 24
In the context of evaluating a fine-tuned LLM for a text classification task, which experimental design technique ensures robust performance estimation when dealing with imbalanced datasets?

QUESTION 25
In the context of language models, what does an autoregressive model predict?

QUESTION 26
Transformers are useful for language modeling because their architecture is uniquely suited for handling which of the following?

QUESTION 27
When should one use data clustering and visualization techniques such as tSNE or UMAP?

QUESTION 28
What metrics would you use to evaluate the performance of a RAG workflow in terms of the accuracy of responses generated in relation to the input query? (Choose two.)

QUESTION 29
Which technique is designed to train a deep learning model by adjusting the weights of the neural network based on the error between the predicted and actual outputs?

QUESTION 30
What is the Open Neural Network Exchange (ONNX) format used for?

QUESTION 31
Imagine you are training an LLM consisting of billions of parameters and your training dataset is significantly larger than the available RAM in your system. Which of the following would be an alternative?

QUESTION 32
In the context of evaluating a fine-tuned LLM for a text classification task, which experimental design technique ensures robust performance estimation when dealing with imbalanced datasets?

QUESTION 33
In Natural Language Processing, there are a group of steps in problem formulation collectively known as word representations (also word embeddings). Which of the following are Deep Learning models that can be used to produce these representations for NLP tasks? (Choose two.)

QUESTION 34
In the Transformer architecture, which of the following statements about the Q (query), K (key), and V (value) matrices is correct?

QUESTION 35
Which of the following claims is correct about quantization in the context of Deep Learning? (Pick the 2 correct responses)

QUESTION 36
Which technology will allow you to deploy an LLM for production application?

QUESTION 37
When preprocessing text data for an LLM fine-tuning task, why is it critical to apply subword tokenization (e.
g., Byte-Pair Encoding) instead of word-based tokenization for handling rare or out-of-vocabulary words?

QUESTION 38
In the context of preparing a multilingual dataset for fine-tuning an LLM, which preprocessing technique is most effective for handling text from diverse scripts (e.g., Latin, Cyrillic, Devanagari) to ensure consistent model performance?

QUESTION 39
You have developed a deep learning model for a recommendation system. You want to evaluate the performance of the model using A/B testing. What is the rationale for using A/B testing with deep learning model performance?