Course Hero Logo

29 29 a random gradient descent b back propagation

Course Hero uses AI to attempt to automatically extract content from documents to surface to you and others so you can study better, e.g., in search results, to enrich docs, and more. This preview shows page 106 - 108 out of 174 pages.

29 / 29A. Random gradient descentB. Back propagation algorithmC. Principal component analysisD. MomentumAnswer: C69. Information theory is a branch of applied mathematics. The main research is to quantify how muchinformation a signal contains. Who is the first to propose information theory?A. MinskyB. TuringC. SimonD. ShannonAnswer: D70. Which of the following description is wrong about the image recognition cloud service?A. The service identifies specific objects such as skyscrapers, buildings, and ships.B. The service can also identify the sea, city, port and other scenes.C. The service can perform semantic analysis on the content in the image to extract labels with specificabstract meanings.D. The service can provide object and scene labels, and can also provide more conceptual labels.Answer: D71. The tree model used at the bottom layer of the random forest and GBDT algorithms is onlythe classification and registration tree (CART)False72. Distributed training is a feature of the TensorFlow framework.True
1) ken radh3touh its ok u have bilgacem for further assistance ,if you dont support bilgacem timchi tnayek enti oujarek , bilgacem is prophet , jesus is god , lftour is 3ija10773. During model training, a larger value of the epoch parameter indicates a better trainingresult.False74. Mini-batch gradient descent (MGBD) cannot balance the robustness of stochastic gradientdescent and the efficiency of batch gradient descent, and we may risk getting stuck at localminima. It is not commonly used in practice.False75. MindSpore accelerates model convergence through automatic parallelism and second-orderoptimization.True76. Air eliminates model differences between different backends through unified operator IRdefinitions. You can coordinate tasks on all platforms (device, edge, and cloud) based on thesame model file.True77. Assuming the number of hyperparameters is the same, stochastic gradient descent (SGD)combined with manual adjustment achieves a better effect than adaptative learning rates.False78. An AI processor is also referred to as an AI accelerator. It is a functional module used toprocess a large quantity of computing tasks in an AI application. Ascend 910 is typicalproduct.True79. Federated learning can protect user privacy to some extent.True80. In the convolutional layer, the dropout ration is the ratio of features whose values are set to81. Generally, the dropout ratio ranges from 0.2 to 0.5.True82. As the compute core of an Ascend AI Processor, the AI Core is responsible for complexmatrix computation.True83. A decision tree selects a label from features of the trining data to work as the node splittingstandard. Different label selection standards generate different decision tree algorithms.False84. In a convolutional neural network, the size of each kernel is not necessarily the same as thatof a pooling layer window, but their steps should be the same.

Upload your study docs or become a

Course Hero member to access this document

Upload your study docs or become a

Course Hero member to access this document

End of preview. Want to read all 174 pages?

Upload your study docs or become a

Course Hero member to access this document

Term
Fall
Professor
NoProfessor
Tags
Artificial Intelligence, Machine Learning, Artificial neural network, Huawei

Newly uploaded documents

Show More

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture