No account needed. Every question explains why every answer is right or wrong, just like the full bank.
lock_openFree sampleCore Machine Learning and AI Knowledgemedium
A pipeline ingests 16-bit greyscale medical images and feeds them into a convolutional network. Before training, each pixel value is divided by 65535 so the resulting tensor contains values in the range 0 to 1. What is the primary reason for this operation?
ATo normalise input values so that large pixel magnitudes do not cause unstable gradients during back-propagation, improving training convergence.check_circle Correct
BTo reduce the spatial resolution of the image so that fewer parameters are needed in the first convolutional layer.
CTo convert the integer pixel values into a floating-point representation that is compatible with the network's activation functions and loss computation.
DTo apply zero-mean standardisation so that each channel has a mean of zero and a standard deviation of one before entering the network.
Explain why pixel-value normalisation is applied to image tensors before neural-network training. Dividing raw pixel values by the maximum representable value maps all inputs to the closed interval 0 to 1. Neural networks trained on unnormalised inputs with very large magnitudes experience large activation values, which produce large loss gradients and can cause weight updates to overshoot, destabilising training. Bounded inputs keep the gradient signal well-conditioned throughout back-propagation, which is the primary purpose of this pre-processing step.
Why A is correct: Scaling inputs to a small, bounded range keeps weight gradients in a workable magnitude, preventing exploding gradients and accelerating convergence - the canonical motivation for input normalisation.
Why B is wrong: Dividing pixel values by a constant does not alter the spatial dimensions of the tensor; downsampling requires pooling or strided convolutions, not scalar division.
Why C is wrong: Casting to float is a necessary step, but the division itself is not required for the cast; the primary motivation is gradient stability from bounded inputs, not merely the numeric type.
Why D is wrong: Dividing by the maximum value scales to the unit interval but does not produce zero-mean output; standardisation requires subtracting the dataset mean and dividing by its standard deviation.
lock_openFree sampleData Analysis and Visualizationmedium
A data engineer needs to extract structured fields (product name, price, and availability) from thousands of unstructured product descriptions and load them into a database. Which prompting strategy most reliably produces machine-parseable output from an LLM for this pipeline?
AZero-shot chain-of-thought prompting, asking the model to reason step-by-step before naming each field
BEmbedding each product description and storing the vector, then using cosine similarity to retrieve the closest known structured record
CFew-shot prompting with plain-text examples separated by delimiter lines, leaving the output format for the model to infer
DStructured-output prompting with a JSON schema in the system prompt, constraining the model to emit a fixed key-value object per descriptioncheck_circle Correct
Identify structured-output prompting as the reliable technique for extracting machine-parseable fields from unstructured text at scale. When an LLM must feed a downstream parser, the output format must be deterministic. Structured-output prompting - declaring a JSON or similar schema inside the prompt and, where the API supports it, using response format constraints - forces the model to emit a fixed shape every time. Chain-of-thought and few-shot approaches improve reasoning or style but leave format under-constrained. Embeddings address search and clustering, not field extraction.
Why A is wrong: Chain-of-thought improves reasoning but produces verbose prose, not a consistent machine-parseable format. Downstream parsers would struggle with inconsistent output shapes across thousands of descriptions.
Why B is wrong: Embeddings plus similarity search retrieves similar items but does not extract fields from the source text. This is a search or clustering technique, not an extraction approach.
Why C is wrong: Few-shot examples guide style but do not enforce a schema. Without an explicit format constraint the model may vary its output structure across samples, breaking automated parsing.
Why D is correct: Structured-output prompting binds the model to a declared schema, guaranteeing field names and types. This is the standard approach for LLM-to-database pipelines where downstream code must parse every response identically.
lock_openFree samplePerformance Optimizationhard
A team is deploying a multimodal inference service on Kubernetes. Each pod requires one GPU for model execution. The NVIDIA device plugin is installed on the cluster. Which resource request configuration in the pod spec correctly reserves a single GPU for the container?
ASet resources.requests to cpu: 0 and memory: 0, then annotate the pod with nvidia.com/gpu: 1 in the metadata section.
BSet resources.limits to gpu: 1 using the standard Kubernetes resource name and omit the vendor prefix entirely.
CSet resources.requests and resources.limits both to nvidia.com/gpu: 1 under the container spec.check_circle Correct
DSet resources.requests to nvidia.com/gpu: 1 only, leaving resources.limits unset, so the pod can burst beyond one GPU when the node has capacity.
Correctly configure GPU resource requests and limits using the NVIDIA device plugin in a Kubernetes pod spec. The NVIDIA device plugin registers each GPU on a node as the extended resource nvidia.com/gpu. Kubernetes treats extended resources as integer quantities with no overcommit: the scheduler only allocates them when both resources.requests and resources.limits carry the same value. Setting both to 1 under the container spec is therefore the required pattern to reserve a single GPU for an inference container.
Why A is wrong: Kubernetes annotations are informational metadata and have no effect on resource scheduling. Extended resources like GPUs must appear in the resources block, not as annotations, to be recognised by the scheduler.
Why B is wrong: gpu is not a standard Kubernetes resource name. The NVIDIA device plugin registers GPUs under the vendor-prefixed extended resource nvidia.com/gpu; omitting the prefix means the scheduler cannot locate or allocate the device.
Why C is correct: The NVIDIA device plugin exposes GPUs as the extended resource nvidia.com/gpu. Kubernetes requires that extended resources be specified identically in both requests and limits, so setting both to 1 correctly reserves one GPU for the container.
Why D is wrong: Extended resources in Kubernetes do not support burst behaviour. The scheduler requires that limits equal requests for any extended resource; specifying only a request without a matching limit causes the pod to be rejected at admission.
The NVIDIA-Certified Associate: Generative AI Multimodal (NCA-GENM) exam has 50 to 60 questions and runs for 60 minutes. The format is multiple choice, online proctored.
What score do I need to pass NCA-GENM?
NVIDIA does not publish a fixed pass mark for NCA-GENM, so treat any "X%" figure you see elsewhere as unofficial. Examworthy gives you a per-domain readiness score so you can judge when you are ready across every domain.
How much does the NCA-GENM exam cost?
The exam costs 125 USD to sit. Practising on Examworthy is free to start, and every answer is explained, right and wrong.
Is there a NCA-GENM practice exam?
Yes. Examworthy's exam mode runs a timed NCA-GENM practice exam (mock) paced to match the real exam, scored per domain so you can see exactly where you stand. Timed mocks are free with an account.
How does Examworthy help me prepare for NCA-GENM?
Every practice question explains why the right answer is right and why each wrong one is wrong, mapped to the official blueprint domains. You learn the reasoning, not just the letter.
Is Examworthy affiliated with NVIDIA?
No. Examworthy is not affiliated with or endorsed by NVIDIA. Our questions are original, blueprint-aligned practice material; we never reproduce live exam items.
Related certifications
More certifications you can practise on Examworthy, related to NVIDIA-Certified Associate: Generative AI Multimodal.
Examworthy is not affiliated with or endorsed by NVIDIA. All questions are original, blueprint-aligned practice material. We never reproduce live exam items. NCA-GENM and related marks belong to their respective owners.
