AI-900T00: Microsoft Azure AI Fundamentals Quiz Questions and Answers

Answer :
  • A) Overfitting
    B) Underfitting
    C) Bias
    All of the above

Explanation :

Overfitting, underfitting, and bias are all common challenges in computer vision. Overfitting occurs when a model is too complex and fits the training data too closely, underfitting occurs when a model is too simple and does not fit the training data well, and bias occurs when a model is not able to capture the true underlying relationship between the input and output.
Answer :
  • Principal Component Analysis (PCA)

Explanation :

Principal Component Analysis (PCA) is a common technique used in computer vision to reduce the dimensionality of image data. Convolutional Neural Networks (CNNs) are used for image classification, Recurrent Neural Networks (RNNs) are used for sequence data, and Support Vector Machines (SVMs) are used for classification and regression.
Answer :
  • Probabilistic values based on correlations found in training data

Explanation :

Machine learning models are trained using historic data, and rely on algorithms that find statistical relationships in the data. Predictions are generally based on probability; and while models are often extremely accurate, predictions are based on a confidence score that indicates a level of probability.
Answer :
  • Object detection

Explanation :

Object detection is a common application of computer vision, which involves identifying and localizing objects within an image. Sentiment analysis is a natural language processing task, speech recognition is a task in speech processing, and time series forecasting is a task in machine learning.
Answer :
  • Model destruction and disposal

Explanation :

The four stages in a responsible generative AI solution are data collection and curation, model training and evaluation, model deployment and monitoring, and model retraining and refinement. Model destruction and disposal is not a stage in a responsible generative AI solution.
Answer :
  • Image recognition

Explanation :

Large language models are designed to process and analyze text-based data, such as natural language processing tasks like text summarization, sentiment analysis, and language translation. Image recognition is not a capability of large language models.
Answer :
  • To generate prompts for generative AI models

Explanation :

Copilots are used to generate prompts for generative AI models, which can help improve the quality of the generated output. Copilots can be human experts or other AI models that are used to provide guidance and feedback to the generative AI model.
Answer :
  • To improve the accuracy of the model

Explanation :

Data augmentation is a technique used to increase the size of the dataset by applying transformations to the existing images. This helps to improve the accuracy of the model by exposing it to more variations of the same image.
Answer :
  • To reduce overfitting

Explanation :

Regularization is used to reduce overfitting in a machine learning model. This involves adding a penalty term to the loss function, which encourages the model to have smaller weights and reduces the complexity of the model.