Free Huawei H13-321_V2.5 Practice Exam with Questions & Answers

The Transformer model architecture includes:

Encoder:Encodes the input sequence into contextualized representations.

Decoder:Uses the encoder output and self-attention over previously generated tokens to produce the target sequence.

Exact Extract from HCIP-AI EI Developer V2.5:

"The Transformer consists of an encoder-decoder structure, with self-attention mechanisms in both components for sequence-to-sequence learning."

Gamma correction is anon-linearimage processing method used to adjust brightness and contrast. It is not limited to grayscale images — it can be applied to both grayscale and color images by operating on individual channels.

γ < 1:Enhances dark regions (brightens shadows) and compresses highlights.

γ > 1:Enhances bright regions and compresses dark regions.It is based onpower-law (exponential) transformation, making it effective for adjusting human-perceived luminance.

Exact Extract from HCIP-AI EI Developer V2.5:

"Gamma correction is a non-linear brightness adjustment based on power-law transformation. It applies to both grayscale and color images. For γ<1, dark regions are brightened; for γ>1, bright regions are enhanced."

Traditional word representations like one-hot vectors are sparse and orthogonal, failing to capture semantic similarities.Distributed semantic representations(word embeddings) map words to dense, continuous vectors in a multi-dimensional space where similar words have similar vector representations. This approach enables better generalization and semantic reasoning in NLP tasks.

Exact Extract from HCIP-AI EI Developer V2.5:

"Distributed semantic representation maps words to dense real-valued vectors in continuous space, allowing semantic similarity to be captured in vector geometry."

TheVision Transformer (ViT)applies the transformer architecture to image patches. Its key advantage is the use ofself-attentionto capture global dependencies and relationships between all parts of an image. This allows ViT to excel in classification accuracy, especially on large datasets with sufficient pre-training.

Exact Extract from HCIP-AI EI Developer V2.5:

"ViT applies self-attention to image patches, enabling global feature extraction and improving classification performance compared to local receptive fields in CNNs."

NER(Named Entity Recognition) is a core NLP task that involves locating and categorizing entities within text into predefined categories like persons, organizations, places, dates, monetary values, and percentages. NER is widely used in information extraction, question answering, and knowledge graph construction.

Exact Extract from HCIP-AI EI Developer V2.5:

"NER identifies and classifies named entities in text into categories such as person names, organizations, locations, time expressions, and numeric values."

In anencoder-decoderarchitecture:

Theencoderprocesses variable-length inputs and encodes them into fixed-length context vectors that summarize the input. (Cis correct.)

Thedecodergenerates output sequences from this context, which may be of variable length.

Adescribes the decoder incorrectly;Bmixes roles;Dis false because output length depends on the target sequence, not the encoder output length.

Exact Extract from HCIP-AI EI Developer V2.5:

"The encoder transforms variable-length sequences into context vectors, which the decoder uses to generate variable-length outputs."

To address overfitting, HCIP-AI EI Developer V2.5 outlines multiple strategies:

Dropout:A regularization method that randomly ignores certain neurons during training, preventing reliance on specific paths and improving generalization.

Data augmentation:Expands the training dataset by applying transformations (rotation, scaling, flipping) to existing data, increasing diversity and reducing overfitting risk.

Parameter norm penalties:Techniques such as L1 and L2 regularization add a penalty to large parameter values, discouraging overly complex models.

Using amore complex model(Option B) is the opposite of what is recommended, as it generally increases the risk of overfitting.

Exact Extract from HCIP-AI EI Developer V2.5:

"Common overfitting mitigation techniques include data augmentation to expand datasets, dropout to randomly deactivate neurons during training, and applying regularization penalties to constrain model complexity."

Historically, NLP has evolved through three main methodological phases:

Rule-based methods— used in early systems, relying on manually crafted grammar and lexicons.

Statistics-based methods— introduced probabilistic models such as HMMs and n-grams.

Deep learning-based methods— using neural networks, transformers, and embeddings.

A “recursion-based method” has never been recognized as a distinct NLP methodology, even though recursion can appear in linguistic theory, it is not a primary computational approach in NLP history.

Exact Extract from HCIP-AI EI Developer V2.5:

"The evolution of NLP includes rule-based, statistical, and deep learning–based methods. Recursion-based approaches are not considered a formal method in NLP development history."

The convolutional layer in CNNs is optimized for spatial feature extraction:

Local connectivity(A) reduces computation and memory usage.

Parameter sharing(B) reduces the number of learnable parameters and helps prevent overfitting.

Stride control(C) allows adjusting the output resolution and computational cost.

Sliding kernel operation(D) extracts local patterns without manual feature definition.

Exact Extract from HCIP-AI EI Developer V2.5:

"CNN convolutional layers leverage local connectivity, parameter sharing, and stride control to efficiently extract local features, reducing computational requirements compared to fully-connected layers."

In CNN usage:

A:True — color images have multiple channels (e.g., RGB = 3), while text inputs are represented as sequences of word embeddings, typically single-channel in structure.

B:True — in text tasks, the convolution kernel height must match the embedding dimension to capture complete token information, which is not a constraint in images.

C:False — there are clear differences in handling between text and image data.

D:False — CNNs can perform very well in text classification when used appropriately.

Exact Extract from HCIP-AI EI Developer V2.5:

"In text CNNs, convolution kernels span the entire embedding dimension, whereas in image CNNs, kernel size is independent of channel count."