Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
429 views15 pages

Preguntas HCIA

Logical reasoning is a core area of AI. Softmax cannot be used for multiple classification problems while malformed data differs from dirty data. When evaluating medical image models, recall is more important than precision. TensorFlow 2.0 uses Keras and eager execution, while Adam is the built-in Keras optimizer. Cifar10 is a Keras dataset and Scikit-learn provides machine learning tools for Python. Voice recognition converts text to audio, and automatic graph segmentation is key to MindSpore. Backpropagation improves gradient descent efficiency using dynamic programming. Jobs requiring social skills are hard to replace, and face analysis services return labels and gender. Atlas chips require CUDA like other GPUs, and neural network layers are hyperparameters. HiAI supports frameworks like

Uploaded by

deditoz
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
429 views15 pages

Preguntas HCIA

Logical reasoning is a core area of AI. Softmax cannot be used for multiple classification problems while malformed data differs from dirty data. When evaluating medical image models, recall is more important than precision. TensorFlow 2.0 uses Keras and eager execution, while Adam is the built-in Keras optimizer. Cifar10 is a Keras dataset and Scikit-learn provides machine learning tools for Python. Voice recognition converts text to audio, and automatic graph segmentation is key to MindSpore. Backpropagation improves gradient descent efficiency using dynamic programming. Jobs requiring social skills are hard to replace, and face analysis services return labels and gender. Atlas chips require CUDA like other GPUs, and neural network layers are hyperparameters. HiAI supports frameworks like

Uploaded by

deditoz
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 15

1..

- Logical reasoning is a par of AI

2.- Softmax can’t be used for multiple classification problems.

3.- Malformed data is not dirty data

4.- In a medical image recognition task, we usually are more concerned about the recall ratio than
the precision ratio when evaluating model performance.

5.- TensorFlow2.0 uses Keras and eager execution to easily model

6.- The Adam optimizar in TensorFlow 2.0 is the built-in optimizer of the Keras module

7.- Cifar10 is a built-in data set of Keras

8.- Scikit-learn is a free software machine learning library for Python. It has powerful tools for data
analysis and mining

9.- Voice recognition refers to the recognition of text data as audio data

10.- Automatic graph segmentation is one of the key technologies of MindSpore

11.- If the metrics parameter is not specified in Model.compile, no loss value will be output

12.- AI is the core research area of machine learning

13.- Pytorch supports GPU acceleration.

14.- Backpropagation makes gradient descent more efficient by means of dynamic programming

15.- Jobs that are innovate and have high requirements on social capabilities cannot be easily
replaced by AI.

16.- When using the face comparison service, the gender of the person is also one the return
values.

17.- After the image label service is called, only one coresponding label value is returned

18.- Atlas series chips need the support of CUDA software package like other GPU accelerator
cards

19.- Similar to a hidden layer, the quantify of neurons at both an input layer and an output of a
neural network is a hiperparameter that can be adjusted.

20 The HiAI mobile computing platform architecture supports various mainstream front-end
frameworks, such as TensorFlow an Caffe.
Ç

You might also like