Fundamentals of machine learning and neural networks: Practice Questions — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)

Practice Questions: Fundamentals of Machine Learning and Neural Networks

These multiple-choice questions are designed to help candidates prepare for the NVIDIA-Certified Associate: Generative AI LLM exam by testing core concepts in machine learning and neural networks.

1. Which of the following best describes supervised learning?

   • A. Learning patterns from unlabeled data
   • B. Learning from labeled input-output pairs
   • C. Learning by trial and error without feedback
   • D. Learning by clustering similar data points

   Answer: B

   Explanation: Supervised learning involves training a model on labeled data where the correct outputs are provided, enabling the model to learn input-output mappings.

2. What is the primary role of an activation function in a neural network?

   • A. To initialize the weights of the network
   • B. To introduce non-linearity into the model
   • C. To reduce the dimensionality of input data
   • D. To perform gradient descent optimization

   Answer: B

   Explanation: Activation functions introduce non-linearities that allow neural networks to learn complex patterns beyond linear relationships.

3. Which architecture is most commonly used for processing sequential data such as text?

   • A. Convolutional Neural Networks (CNNs)
   • B. Recurrent Neural Networks (RNNs)
   • C. Feedforward Neural Networks
   • D. Autoencoders

   Answer: B

   Explanation: RNNs are designed to handle sequential data by maintaining internal states that capture temporal dependencies.

4. What is the purpose of transfer learning in deep learning?

   • A. To train a model from scratch on a large dataset
   • B. To use a pre-trained model on a new but related task
   • C. To increase the size of the training dataset artificially
   • D. To optimize hyperparameters automatically

   Answer: B

   Explanation: Transfer learning leverages knowledge from a pre-trained model to improve learning efficiency and performance on a related task with less data.

5. During training, which technique helps prevent overfitting by randomly disabling neurons?

   • A. Batch normalization
   • B. Dropout
   • C. Gradient clipping
   • D. Early stopping

   Answer: B

   Explanation: Dropout randomly disables neurons during training to reduce overfitting by preventing co-adaptation of neurons.

6. Which loss function is typically used for multi-class classification problems?

   • A. Mean Squared Error (MSE)
   • B. Binary Cross-Entropy
   • C. Categorical Cross-Entropy
   • D. Hinge Loss

   Answer: C

   Explanation: Categorical cross-entropy is used for multi-class classification to measure the difference between predicted probabilities and true class labels.

7. What does the term "epoch" refer to in the context of training deep learning models?

   • A. One forward pass through the network
   • B. One backward pass through the network
   • C. One complete pass through the entire training dataset
   • D. The number of layers in the neural network

   Answer: C

   Explanation: An epoch is one full iteration over the entire training dataset during model training.

More in this topic

Fundamentals of machine learning and neural networks: Quick Reference — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)Leveraging transfer learning for efficient results — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)Fundamentals of machine learning and neural networks: Common Mistakes — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)Applying fundamental techniques to train deep learning models — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)Core Machine Learning and AI Knowledge — NVIDIA-Certified Associate: Generative AI LLMFundamentals of machine learning and neural networks: Worked Example — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)Fundamentals of machine learning and neural networks — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)Deep learning model architectures — Core Machine Learning and AI Knowledge (NVIDIA-Certified Associate: Generative AI LLM)