H13-321_V2.5 Questions and Answers

In Huawei Cloud ModelArts training jobs, theHyperparameterparameter is explicitly designed to allow users to define custom training settings, such as learning rate, batch size, and number of epochs.

Algorithm Typespecifies the model algorithm.

Resource Poolselects the computational environment.

Compute Nodesdetermines the number of nodes used for training.

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

"The Hyperparameter field in ModelArts allows users to define and pass custom training parameters to the algorithm for tuning performance."

In Python'sjiebalibrary, the cut() method is used for Chinese word segmentation. It splits a given sentence into individual words based on probabilistic models and a dictionary. The method supports both precise mode and full mode, with precise mode being the default for balanced accuracy and completeness.

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

"The jieba.cut() method segments Chinese text into words, supporting multiple modes for different application needs."

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."

In NLP:

Text classification(e.g., sentiment analysis) predicts a single label for the entire input sequence.

Sequence labeling(e.g., Named Entity Recognition, Part-of-Speech tagging) produces an output label for each token or position in the input sequence.This distinction is important for selecting appropriate model architectures and loss functions.

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

"Text classification assigns one label to the whole text, whereas sequence labeling assigns a label to each token in the sequence."

An object detection system must:

Classifythe detected object (A).

Locatethe object by generating bounding box coordinates (C).

Estimate confidencescores indicating prediction reliability (D).

Object contour calculation (B) is a separate task often related toinstance segmentation, not general object detection.

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

"Object detection includes classification, bounding box localization, and confidence score prediction. Contour detection belongs to segmentation tasks."

FastTextis an extension of Word2Vec developed by Facebook AI Research. Unlike Word2Vec, which learns embeddings for whole words, FastText represents each word as a sum of its character n-gram embeddings. This helps in handling rare words and morphologically rich languages by generating embeddings for unseen words from their subword components.

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

"FastText decomposes words into character n-grams and represents words as the sum of their n-gram vectors, improving representation for rare and out-of-vocabulary words."

MFCCs are a widely used feature extraction method in speech recognition. The process involves:

Converting the time-domain signal to the frequency domain using the Fourier transform.

Mapping the frequency scale to theMel scaleto mimic human hearing perception.

Taking the logarithm of the power spectrum to emphasize perceptually important differences.

Applying the discrete cosine transform (DCT) to obtaincepstral coefficients.

These steps capture the spectral envelope, which is important for distinguishing phonemes in speech.

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

"MFCCs transform audio to the Mel scale, applying log compression and cepstral transformation to align with human auditory characteristics."

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."

In hybridDNN-HMMspeech recognition:

TheDNNacts as an acoustic model, transforming audio features into probability estimates for phonetic states.

TheHMMmodels the temporal sequence and transitions between phonetic states, handling time dependencies and variability in speech.

This combination leverages the representational power of DNNs and the sequence modeling strengths of HMMs.

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

"In DNN-HMM systems, the DNN outputs state posterior probabilities, and the HMM models the temporal sequence structure of speech."

Pixel adjacency describes how pixels are connected:

4-adjacency:Pixels share a side (up, down, left, right).

Diagonal adjacency:Pixels touch at a corner.

8-adjacency:Combination of 4-adjacency and diagonal adjacency.

Given coordinates (21,13) and (22,12), the pixels differ by 1 in both x and y directions, meaning they meet at a corner — this isdiagonal adjacency. Since 8-adjacency includes both side and diagonal adjacency, they are also8-adjacent.

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

"In 8-adjacency, pixels are considered neighbors if they are connected horizontally, vertically, or diagonally. Diagonal adjacency occurs when pixels touch at a corner."

When the contrast between bright and dark areas is extreme,gamma correctionis effective in adjusting luminance in a non-linear way to balance these extremes.

Ifγ < 1, dark areas are brightened, highlights are compressed.

Ifγ > 1, bright areas are emphasized, shadows are compressed.Other methods like grayscale stretching and compression target linear contrast changes, while inversion flips pixel values but doesn’t balance extreme light/dark ranges effectively.

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

"Gamma correction adjusts image brightness non-linearly, suitable for correcting overly bright or overly dark regions, improving overall visibility."

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."

Word vector evaluation can be:

Intrinsic:Directly tests vector properties via word similarity and analogy tasks.

Extrinsic:Tests in downstream applications.

A:True — word similarity tasks use human-labeled datasets and cosine similarity.

B:True — intrinsic evaluations include similarity and analogy tasks.

C:True — analogy tests assess how well vectors capture semantic relationships.

D:False — both intrinsic and extrinsic methods are valuable, but intrinsic methods are more common for initial evaluations.

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

"Intrinsic evaluations (similarity, analogy) test embedding quality directly, while extrinsic evaluations measure impact on real tasks."