Neural Networks MCQ Test: Neural Networks MCQs - Practice Questions
1. Discuss the concept of 'neuroevolution' and how it differs from traditional gradient-based optimization in neural networks.
2. What is 'unsupervised learning' in the context of neural networks, and provide an example of its application.
3. Discuss the challenges and solutions associated with 'imbalanced datasets' in the training of neural networks.
4. Discuss the concept of 'adversarial attacks' on neural networks and strategies to enhance model robustness against such attacks.
5. What is the 'Kullback-Leibler (KL) divergence' and how is it used in the context of probabilistic models and neural networks?
6. What does 'gradient descent' optimize during neural network training?
7. Explain the concept of 'attention mechanism' in neural networks and its role in natural language processing.
8. Explain the concept of 'spiking neural networks' and their potential advantages in simulating biological neuron behavior.
9. What is a 'hyperparameter' in the context of neural networks?
10. What challenges does 'long-term dependency' pose in traditional recurrent neural networks (RNNs), and how are they addressed in more advanced architectures like LSTMs?