A) Unsupervised learning.
B) Semi-supervised learning.
C) Reinforcement learning.
D) Supervised learning.

A) Data storage.
B) Pattern recognition and classification.
C) Writing code.
D) Network security.

A) A model that learns faster.
B) A model that is too complex and performs poorly on new data.
C) A model with no parameters.
D) A model that generalizes well.

A) Genetic algorithms.
B) Support Vector Machines.
C) Gradient descent.
D) K-means clustering.

A) To classify data into categories.
B) To optimize linear equations.
C) To learn behaviors through trial and error.
D) To map inputs to outputs directly.

A) The power consumption of a system.
B) The processing speed of a computer.
C) The storage capacity of a computer.
D) The ability of a machine to exhibit intelligent behavior equivalent to a human.

A) Easier to implement than standard algorithms.
B) Works better with small datasets.
C) Ability to automatically learn features from data.
D) Requires less data than traditional methods.

A) Linear regression.
B) Random forests.
C) Decision trees.
D) K-means.

A) Extracting patterns and information from large datasets.
B) Cleaning data for analysis.
C) Encrypting data for security.
D) Storing large amounts of data in databases.

A) Convolutional Neural Networks (CNNs).
B) Radial basis function networks.
C) Feedforward neural networks.
D) Recurrent Neural Networks (RNNs).

A) Iteration through random sampling.
B) Function approximation.
C) Sorting through quicksort.
D) Survival of the fittest through evolution.

A) Data that is too small for analysis.
B) Private user data collected by apps.
C) Large and complex datasets that require advanced tools to process.
D) Data stored in a relational database.

A) Geometric transformations.
B) The Internet.
C) Statistical models.
D) The structure and functions of the human brain.

A) To increase training data size.
B) To evaluate model performance during training.
C) To replace test sets.
D) To make models happier.

A) Pygame.
B) Flask.
C) Scikit-learn.
D) Beautiful Soup.

A) Minimizing the distance between all points.
B) Maximizing the volume of the dataset.
C) Finding the hyperplane that best separates data points.
D) Using deep learning for classification.

A) Transfers data between different users.
B) Uses knowledge gained from one task to improve performance on a related task.
C) Moves software applications between platforms.
D) Shifts models from one dataset to another without changes.

A) Bias in data and algorithms.
B) Uniform coding standards.
C) Too much public interest.
D) Hardware limitations.

A) HTML.
B) Python.
C) C++.
D) Assembly.

A) Prediction
B) Regression
C) Classification
D) Clustering

A) Decision Trees
B) Monte Carlo Simulation
C) Gradient Descent
D) Genetic Algorithms

A) Entropy
B) Accuracy
C) Throughput
D) Variance

A) TensorFlow
B) Windows
C) MySQL
D) Git

A) Bandwidth
B) Overfitting
C) Throughput
D) Latency

A) Basic arithmetic calculations.
B) Natural language processing.
C) Spreadsheets.
D) Word processing.

A) K-means clustering.
B) Genetic algorithms.
C) Linear regression.
D) Reinforcement learning.

A) Support Vector Machine.
B) Q-learning.
C) Linear regression.
D) K-means clustering.