AI Fundamentals - MCQ Practice Questions

The Minimax Algorithm is specifically designed for two-player adversarial games. One player (MAX) tries to maximize the score while the other (MIN) tries to minimize it. The algorithm explores the game tree and selects the optimal move assuming both players play perfectly. A* and Dijkstra's are pathfinding algorithms, and Greedy Best-First Search does not account for adversarial behavior.

Overfitting occurs when a model learns not only the underlying patterns but also the noise and random fluctuations in the training data. This causes excellent performance on training data but poor generalization to unseen (test) data. Option A describes underfitting in part, Option C fully describes underfitting, and Option D refers to a computational issue, not overfitting.

ReLU (Rectified Linear Unit), defined as $f(x)=\max (0,x)$, is the most widely used activation function in hidden layers of deep networks. Unlike Sigmoid and Tanh, ReLU does not saturate for positive inputs, which significantly alleviates the vanishing gradient problem and speeds up training. Softmax is typically used only in the output layer for multi-class classification.

TF-IDF stands for Term Frequency-Inverse Document Frequency. It is a numerical statistic used in information retrieval and NLP to reflect how important a word is to a document in a collection or corpus. Term Frequency (TF) measures how often a term appears in a document, while Inverse Document Frequency (IDF) penalizes terms that appear in many documents, thus highlighting unique and meaningful words.

Proposed by Alan Turing in 1950, the Turing Test is a measure of a machine's ability to exhibit intelligent behavior indistinguishable from that of a human. A human evaluator communicates via text with both a human and a machine without knowing which is which. If the evaluator cannot reliably distinguish the machine from the human, the machine is said to have passed the test. It evaluates conversational intelligence, not speed or memory.

A Bayesian Network is a probabilistic graphical model. Each node represents a random variable, and each directed edge between nodes represents a conditional dependency (cause-effect relationship). The strength of each relationship is quantified by conditional probability tables. 'Actions and rewards' belong to reinforcement learning, 'states and transitions' belong to Markov models, and 'features and weights' are concepts from linear models.

K-Nearest Neighbors (KNN) is a non-parametric, lazy (instance-based) learning algorithm used for classification and regression. For a new data point, KNN finds the K closest points in the training set using a distance metric (such as Euclidean distance) and assigns the class by majority vote. K-Means is an unsupervised clustering algorithm, Logistic Regression is parametric, and Naive Bayes is a probabilistic classifier.

Reinforcement Learning (RL) is a type of machine learning where an agent learns to make decisions by interacting with an environment. The agent takes actions, receives feedback in the form of rewards (positive) or penalties (negative), and aims to maximize cumulative reward over time. Option A describes supervised learning, Option B describes unsupervised learning, and Option D describes ensemble learning.

Backpropagation (short for backward propagation of errors) is the core algorithm for training neural networks. It computes the gradient of the loss function with respect to each weight using the chain rule of calculus, propagating the error signal from the output layer back to the input layer. These gradients are then used by an optimization algorithm (like gradient descent) to update the weights and minimize the loss.

STRIPS stands for Stanford Research Institute Problem Solver. It was one of the first automated planners developed at SRI International in 1971 by Richard Fikes and Nils Nilsson. It introduced a formal language to describe planning problems using states, goals, and operators (actions with preconditions and effects), and laid the foundation for modern AI planning languages like PDDL (Planning Domain Definition Language).