NVIDIA Generative AI Multimodal - NCA-GENM Exam Practice Test

A. To measure GPU usage and other metrics with Prometheus. B. To generate images from English text-prompts using CLIP. C. To implement GPU-accelerated data preparation and feature extraction. D. To optimize deep neural network computations on NVIDIA GPUs.

A. Fill in the missing values with a default value. B. Remove the rows with missing values. C. Remove the columns with missing values. D. Analyze the patterns and distribution of missing values.

A. To classify input images as noisy or clean. B. To generate new images from pure noise. C. To detect noisy objects in input images. D. To segment noisy patches in input images.

A. In a multimodal context, usually, contrastive learning increases the similarity of representations across modalities for the different objects and decreases the similarity of representations across modalities for same objects. B. Contrastive learning is a technique used to manipulate and analyze multimodal data using Generative AI. C. Contrastive learning is a technique used to train deep learning models by comparing similar and dissimilar inputs and optimizing the model to maximize the similarity between representations of similar inputs and minimize the similarity between representations of dissimilar inputs. D. In a multimodal context, usually, contrastive learning decreases the similarity of representations across modalities for the same objects and increases the similarity of representations across modalities for different objects. E. In a multimodal context, usually, contrastive learning increases the similarity of representations across modalities for the same objects and decreases the similarity of representations across modalities for different objects.

A. To assign weights to each word in the input sequence. B. To measure the importance of the words in the output sequence. C. To determine the order in which words are generated. D. To capture the order of the words in the input sequence.

A. More advanced natural language processing techniques to interpret radiology reports, ignoring the MRI scans' diagnostic value. B. Directly combining MRI scans and radiology reports into a single input stream without preprocessing or modality-specific adjustments. C. Implementing separate unimodal pipelines for each modality to ensure the data is informative and the model design is accurate. D. Training a deep learning model using the images in the dataset to find outliers and enhancing the quality of MRI scans using image processing techniques.