• What is the difference between normal search and adversarial search?
• Normal Search: Solution = seq. of actions leading to goal. Adversarial
Search: Opponent interfering at every step! Makes move that
maximizes outcome, assuming optimal play by opponent
• What is an example of an adversarial search algorithm?
• 1. Chess: Chess is a classic example of an adversarial search problem.
Each player (White and Black) takes turns making moves while trying
to checkmate their opponent. The search involves evaluating the best
moves while anticipating the opponent's responses.
optimization
• choosing the best option from a set of options
local search
• search algorithms that maintain a single node and searches by
moving to a neighboring node
• Hill Climbing Variants
• Variant Definition
• steepest-ascent choose the highest-valued neighbor
• stochastic choose randomly from higher-valued
neighbors
• first-choice choose the first higher-valued neighbor
• random-restart conduct hill climbing multiple times
• local beam search chooses the k highest-valued neighbors
• supervised learning given a data set of input-output pairs, learn a
function to map inputs to outputs
classification
• supervised learning task of learning a function mapping an input
point to a discrete category
• nearest-neighbor classification
algorithm that, given an input, chooses the class of the nearest data
point to that input
• k-nearest-neighbor classification
• algorithm that, given an input, chooses the most common class out of the k
nearest data points to that input
• maximum margin separator
• boundary that maximizes the distance between any of the data points
• regression
• supervised learning task of learning a function mapping an input point to a
continuous value
• loss function
• function that expresses how poorly our hypothesis performs
• overfitting
• a model that fits too closely to a particular data set and therefore may fail to
generalize to future data
• regularization
• penalizing hypotheses that are more complex to favor simpler, more general
hypotheses
• cost(h) = loss(h) + λcomplexity(h)
• holdout cross-validation
• splitting data into a training set and a test set, such that learning happens on
the training set and is evaluated on the test set
• k-fold cross-validation
• splitting data into k sets, and experimenting k times, using each set as
a test set once, and using remaining data as training set
• reinforcement learning
• given a set of rewards or punishments, learn what actions to take in
the future
• Markov Decision Process
• model for decision-making, representing states, actions, and their
rewards
• function approximation
• approximating Q(s, a), often by a function combining various features,
rather than storing one value for every state-action pair
• unsupervised learning
• given input data without any additional feedback, learn patterns
• clustering
• organizing a set of objects into groups in such a way that similar
objects tend to be in the same group
• Some Clustering Applications
• • Genetic research
• • Image segmentation
• • Market research
• • Medical imaging
• • Social network analysis
• Neural Networks
• Neurons are connected to and receive electrical signals from other neurons.
• Neurons process input signals and can be activated
• artificial neural network
• mathematical model for learning inspired by biological neural networks
• Model mathematical function from inputs to outputs based on the structure
and parameters of the network.
• Allows for learning the network's parameters based on data
gradient descent
algorithm for minimizing loss when training
neural network
• Perceptron
• Only capable of learning linearly separable decision boundary.
multilayer neural network
artificial neural network with an input layer,
an output layer, and at least one hidden layer
backpropagation
algorithm for training neural networks with
hidden layers
• deep neural networks
• neural network with multiple hidden layers
• dropout
• temporarily removing units — selected at random — from a neural
network to prevent over-reliance on certain units
• computer vision
• computational methods for analyzing and understanding digital
images
• image convolution
• applying a filter that adds each pixel value of an image to its neighbors, weighted according to a
kernel matrix
• pooling
• reducing the size of an input by sampling from regions in the input
• max-pooling
• pooling by choosing the maximum value in each region
• convolutional neural network
• neural networks that use convolution, usually for analyzing images
• feed-forward neural network
• neural network that has connections only in one direction
• recurrent neural network
• neural network that generates output that feeds back into its own
inputs
• unconditional probability
• degree of belief in a proposition in the absence of any other evidence
• conditional probability
• degree of belief in a proposition given some evidence that has
already been revealed
• random variable
• a variable in probability theory with a domain of possible values it can
take on
• independence
• the knowledge that one event occurs does not affect the probability
of the other event
• P(a ∧ b) = P(a)P(b|a)
• P(a ∧ b) = P(a)P(b)
• Bayes' Rule
• P(a ∧ b) = P(b) P(a|b)
• P(a ∧ b) = P(a) P(b|a)
• Markov assumption
• the assumption that the current state depends on only a finite fixed
number of previous states
• Markov chain
• a sequence of random variables where the distribution of each
variable follows the Markov assumption
• Hidden Markov Model
• a Markov model for a system with hidden states that generate some
observed event
• sensor Markov assumption
• the assumption that the evidence variable depends only the corresponding state
• Task Definition
• filtering given observations from start until now, calculate distribution for current state
• prediction given observations from start until now, calculate distribution for a future
state
• smoothing given observations from start until now,
• calculate distribution for past state
• most likely explanation given observations from start until now, calculate most likely
sequence of states
• agents that reason by operating on internal representations of
knowledge
• sentence
• an assertion about the world in a knowledge representation language
• model
• assignment of a truth value to every propositional symbol (a "possible
world")
• knowledge base
• a set of sentences known by a knowledge-based agent
• Entailment
•α⊨ β
• In every model in which sentence α is true, sentence β is also true
• inference
• the process of deriving new sentences from old ones
• agent
• entity that perceives its environment and acts upon that environment
• state
• a configuration of the agent and its environment
• initial state
• the state in which the agent begins
• actions
• choices that can be made in a state
• ACTIONS(s) returns the set of actions that can be executed in state s
• transition model
• a description of what state results from performing any applicable action in
any state
• RESULT(s, a) returns the state resulting from performing action a in state s
• state space
• the set of all states reachable from the initial state by any sequence of actions
• goal test
• way to determine whether a given state is a goal state
• path cost
• numerical cost associated with a given path
• Search Problems
• • initial state
• • actions
• • transition model
• • goal test
• • path cost function
• solution
• a sequence of actions that leads from the initial state to a goal state
• optimal solution
• a solution that has the lowest path cost among all solutions
• node
• a data structure that keeps track of
• - a state
• - a parent (node that generated this node)
• - an action (action applied to parent to get node)
• - a path cost (from initial state to node)
• stack
• last-in first-out data type
• depth-first search
• search algorithm that always expands the deepest node in the frontier
• breadth-first search
• search algorithm that always expands the shallowest node in the frontier
• queue
• first-in first-out data type
• uninformed search
• search strategy that uses no problem specific knowledge
• informed search
• search strategy that uses problem-specific knowledge to find solutions more efficiently
• greedy best-first search
• search algorithm that expands the node that is closest to the goal, as
estimated by a heuristic function h(n)
• A* search
• search algorithm that expands node with lowest value of g(n) + h(n)
• g(n) = cost to reach node
• h(n) = estimated cost to goal
• 255,168
• total possible Tic-Tac-Toe games
• 288,000,000,000
• total possible chess games after four moves each
• total possible chess games
• (lower bound)
10^29000
•
