Exam for engine

NO.11 After the ModelArts model training is completed, it supports one-click deployment on the end, edge, and cloud.

NO.12 An APP that can display the plant name and cultivation method after taking a photo of a potted plant. Its core is the use of image segmentation technology.

NO.13 In the experiment of implementing smart albums with Huawei Cloud EI image tags, which of the following descriptions of the error_code response parameter of the image tag API is correct? (Multiple choice)

NO.14 Which of the following is the most important change in the CD-DNN-HMM model?

NO.15 Which of the following descriptions of gradient disappearance and gradient explosion are correct? (Multiple choice)

NO.16 Which of the following is not a method of speech feature extraction?

NO.17 Through image algorithms, the foreground and background of a person in a photo taken with an ordinary mobile phone are segmented, and then () operations are performed on () parts to achieve a blur effect similar to that of a SLR camera.

NO.18 The perceptron is doing a simple binary classification task.

NO.19 What is the main function of the convolution kernel?

NO.20 With the initial probability and transition probability matrix, the probability of any state can be calculated.

NO.21 Speech processing is a general term for technologies used to study the vocalization process, statistical characteristics of speech signals, automatic speech recognition, machine synthesis and speech perception.

NO.22 What types of annotation tasks can be performed in data annotation in ModelArts data management? (Multiple choice)

NO.23 The LDA algorithm assumes that the prior distribution of topics in documents and the prior distribution of words in topics both follow the Dirichlet distribution.

NO.24 The back propagation algorithm is an algorithm used to calculate gradients in neural networks.

NO.25 Use two 3×3 convolution kernels to convolve a three-channel color image. How many channels does the resulting feature map have?

NO.26 Huawei Cloud EI provides a Restful API. Which of the following options is a method for requesting the server to add new resources or perform special operations?

NO.27 Which of the following options is not a commonly used algorithm for keyword extraction?

NO.28 The larger the template size, the better the denoising effect of the mean filter. When performing denoising, a large-sized template should be selected for mean filtering.

NO.29 In which of the following fields does the convolutional neural network perform well?

NO.30 Which of the following options is the algorithm used to estimate the parameters of a single Gaussian model?