IBM IBM Data and AI C1000-059 Questions & Answers

• Question 21:

  What are three elements that are typically part of a machine learning pipeline in scikit-learn or pyspark? (Choose three.)

  A. model building

  B. data preprocessing

  C. model prediction

  D. business understanding

  E. use case selection F. data exploration

  Correct Answer: BCF

  Reference: https://www.analyticsvidhya.com/blog/2019/11/build-machine-learning-pipelines-pyspark/

• Question 22:

  What are the various components that make up a time series data?

  A. trend, noise, covariance

  B. trend, noise, kurtosis

  C. trend, seasonality, causation

  D. trend, seasonality, noise

  Correct Answer: D

• Question 23:

  Which one is the most appropriate use case for artificial intelligence (AI)?

  A. detecting objects in video streams

  B. compressing large video files

  C. aggregating sales revenue per state

  D. creating a pivot table with monthly costs

  Correct Answer: C

• Question 24:

  Considering one ML application is deployed using Kubernetes, its output depends on the data which is constantly stored in the model, if needing to scale the system based on available CPUs, what feature should be enabled?

  A. persistent storage

  B. vertical pod autoscaling

  C. horizontal pod autoscaling

  D. node self-registration mode

  Correct Answer: A

• Question 25:

  Which fine-tuning technique does not optimize the hyperparameters of a machine learning model?

  A. grid search

  B. population based training

  C. random search

  D. hyperband

  Correct Answer: D

  Reference: https://www.datacamp.com/community/tutorials/parameter-optimization-machine-learning- models

• Question 26:

  What are two hyperparameters used when building a k-means model? (Choose two.)

  A. kernel

  B. learning rate

  C. number of iterations

  D. number of clusters

  E. number of neighbors

  Correct Answer: CD

  Reference: https://www.ritchieng.com/machine-learning-clustering-kmeans/

• Question 27:

  What is a class of machine learning problems where the algorithm builds a mathematical model from a set of data that contains both the inputs and the desired outputs?

  A. unsupervised learning

  B. mentoring

  C. reinforcement learning

  D. supervised learning

  Correct Answer: D

  Reference: https://en.wikipedia.org/wiki/Machine_learning

• Question 28:

  Given two multidimensional arrays of the same data type, A and B which two Python NumPy statements give the matrix product of the two matrices? (Choose two.)

  A. A @ B

  B. A x B

  C. A * B

  D. np.matprod(A,B)

  E. np.dot(A,B)

  Correct Answer: CD

• Question 29:

  Which IBM Watson Machine Learning deployment method offers the ultimate flexibility in deploying a machine learning model?

  A. Watson Machine Learning Python client

  B. Watson Machine Learning FORTRAN client

  C. Watson Studio Project

  D. Watson Machine Learning REST API

  Correct Answer: D

  Reference: https://neptune.ai/blog/best-machine-learning-as-a-service-platforms-mlaas

• Question 30:

  Which distance is applied for multivariate outlier detection?

  A. Minkowski distance

  B. Manhattan distance

  C. Mahalanobis distance

  D. Euclidean distance

  Correct Answer: C

  Reference: https://core.ac.uk/download/pdf/233075917.pdf