In time series forecasting, the goal is to predict future ________ based on past observations.
- Events
- Trends
- Weather
- Stock Prices
Time series forecasting aims to predict future trends or patterns based on historical data, which can be applied in various fields like finance or weather.
Decision Trees often suffer from ______, where they perform well on training data but poorly on new, unseen data.
- Overfitting
- Pruning
- Splitting
- Underfitting
Decision Trees are prone to "Overfitting," where they become too complex and fit the training data too closely. This can lead to poor generalization to new, unseen data.
Which of the following techniques is used to estimate future rewards in reinforcement learning?
- Q-Learning
- Gradient Descent
- Principal Component Analysis
- K-Means Clustering
Q-Learning is a technique in reinforcement learning used to estimate future rewards associated with taking actions in different states.
What is the potential consequence of deploying a non-interpretable machine learning model in a critical sector, such as medical diagnosis?
- Inability to explain decisions
- Improved accuracy
- Faster decision-making
- Better generalization
Deploying a non-interpretable model can result in a lack of transparency, making it challenging to understand how and why the model makes specific medical diagnosis decisions. This lack of transparency can be risky in critical sectors.
The ability of SVMs to handle non-linear decision boundaries is achieved by transforming the input data into a higher-dimensional space using a ______.
- Classifier
- Dimensionality Reduction
- Ensemble
- Kernel
SVMs use a mathematical function called a kernel to transform data into a higher-dimensional space, enabling them to handle non-linear decision boundaries effectively.
The multi-armed bandit problem is a classic problem in which domain?
- Sequential Decision-Making Problems
- Natural Language Processing
- Computer Graphics
- Speech Recognition
The multi-armed bandit problem falls under the domain of Sequential Decision-Making Problems, specifically addressing scenarios where a decision must be made over time with limited resources.
In the context of RNNs, what problem does the introduction of gating mechanisms in LSTMs and GRUs aim to address?
- Vanishing and Exploding Gradients
- Overfitting and Data Loss
- Dimensionality Reduction and Compression
- Sequence Length Reduction and Truncation
The introduction of gating mechanisms in LSTMs and GRUs aims to address the problem of vanishing and exploding gradients, which occur during training due to the backpropagation of errors over long sequences. These mechanisms help RNNs capture long-range dependencies in data.
In K-means clustering, the algorithm iteratively updates the cluster centers until the within-cluster sum of squares is ________.
- Minimized
- Equal to 0
- Maximized
- Converged
In K-means clustering, the algorithm aims to minimize the within-cluster sum of squares (WCSS). This represents the total variance within clusters. As the algorithm iteratively updates the cluster centers, the goal is to minimize the WCSS, making "Minimized" the correct option.
In a scenario with noisy data, increasing the value of 'k' in the k-NN algorithm can help to ________ the noise.
- Amplify
- Eliminate
- Introduce
- Preserve
Increasing the value of 'k' in the k-NN algorithm can help eliminate noise. A higher 'k' value smooths the decision boundaries, reducing the impact of individual noisy data points.
Q-learning is a type of ________ learning algorithm that aims to find the best action to take given a current state.
- Reinforcement
- Supervised
- Unsupervised
- Semi-supervised
Q-learning is a type of reinforcement learning that focuses on finding the best action to take in a given state to maximize cumulative rewards.