Chapter 1
- (True or False) By “all AI scenarios”, Huawei means different deployment scenarios for AI, including public clouds, private clouds, edge computing in all forms, industrial IoT devices, and consumer devices.
true
false
- (Multiple-answer question). Which of the following are AI application fields?
Smart household
Smart healthcare
Smart city
Smart education
Chapter 2
- (True or false) Gradient descent iteration is the only method of machine learning algorithms.
true
false
- (Single-answer question. Which of the following algorithms is not supervised learning?
Linear regression
Decision tree
KNN
K-means
Chapter 3
- (True or False).Compared with the recurrent neural network, the convolutional neural network is more suitable for image recognition.
true
false
- (True or False) GAN is a deep learning model, which is one of the most promising methods for unsupervised learning of complex distribution in recent years.
true
false
- (Single-choice).There are many types of deep learning neural networks. Which of the following is not a deep learning neural network?
CNN
RNN
LSTM
Logistic
- (Multi-choice).There are many important “components” in the convolutional neural network architecture. Which of the following are the convolutional neural network “components”?
Activation function
Convolutional kernel
Pooling
Fully connected layer
Chapter 4
- (True or False) In TensorFlow 2.x, eager execution is enabled by default.
true
false
- (Single-choice). Which of the following statements about tf.keras.Model and tf.keras.Sequential is incorrect when the tf.keras interface is used to build a network model?
tf.keras.Model supports network models with multiple inputs, while tf.keras.Sequential does not.
tf.keras.Model supports network models with multiple outputs, while tf.keras.Sequential does not.
tf.keras.Model is recommended for model building when a sharing layer exists on the network.
tf.keras.Sequential is recommended for model building when a sharing layer exists on the network.
Chapter 5
- (Single-choice) In MindSpore, which of the following is the operation type of nn?
Mathematical
Network
Control
Others
Chapter 6
- (Single-choice. What are the main applications of Ascend 310?
Model inference
Model training
Model building
Chapter 7
- (multiple choice) What are the advantages of the HiAI mobile computing platform?
Comprehensive documents
Source code enabling quick start
Different types of APIs
Various tool chains
Chapter 8
- (Multi-choice).Which of the following scenarios can EI be applied to?
Intelligent government
Intelligent city
Intelligent manufacturing
Intelligent finance
- Faced with the challenge of achieving efficient distributed training for ultra-large-scale models, MindSpore is handled as?
- Automatic parallel
- Serial
- Manual parallel
- Which of the following is not the difference between Python 2 and Python 3?
- print
- Unicode
- import
- xrange
- Which of the following options is not central to linear algebra?
- Probability theory
- Linear transformation
- Matrix theory
- Vector space
- The Python dictionary is widely identified by “{}”. and the internal data consists of the key and its corresponding value
- In the process of training the neural network, we use the gradient descent method to continuously update which value, which makes the loss Function minimization?
- Number of samples
- Eigenvalues
- Hyperparameter
- parameter
- Huawei Machine learning Service MLS MLS is a one-stop platform that supports the entire process of data analysis.Which of the following is not a feature of MLS?
- A rich library of machine learning algorithms.
- machine learning program is intuitive and easy to use.
- Distributed and scalable big data computing engine.
- Support for the R language but does not support the Python language
- GBDT Compared with the random forest algorithm, which of the following statements is wrong?
- GBDT Algorithm is easier to underfit than random forest
- Random forest is calculated in parallel, while GBDT Can’t
- GBDT Algorithm is easier to overfit than random forest
- GBDT And random forest are built on CART Based on the tree
- The following code was used when compiling the model: model.compile(optimizer=’Adam,loss=’categorical.crossentropy’,metrics=[tf.keras.metrics.accuracy]), currently using evaluateWhen the method evaluates the model, which of the following indicators will be output?
- accuracy
- categorical_ 1oss
- loss
- categorical accuracy
- According to Huawei Cloud EI Intelligent platform, which of the following solutions can be provided?
- Crowd statistics program
- Policy query scheme based on knowledge graph
- Vehicle identification scheme
- Intrusion recognition scheme
- Which of the following does not belong to long-term memory LSTM (long Short・Term Memory) network architecture?
- Memory door
- Forget the door
- Input door
- Output door