Atlas
Concepts.
The connected concept graph behind every course.
Explore Python concepts from the basics to advanced topics. Each concept is explained in simple language with examples, diagrams and real-world use cases.
- 2892 Concepts
- 12 Core Topics
- A–Z glossary
- Visually explained
Core Topics
Browse all 28922892 concepts
#6 concepts
0-1 LossThe multiclass categorization goal is to learn h : X → [k].19-state random walk taskThe λ-return is presented as a smooth alternative between Monte Carlo and one-step TD met…1D ConvnetsSequence models operate on ordered numeric representations, not raw text.ε-Greedy Action SelectionHigh initial action-value estimates can make a greedy method explore without explicitly u…ε-Greedy PoliciesSarsa control estimates the action values of its current behavior policy.ε-soft policiesOn-policy first-visit MC control alternates between episode generation and policy improve…
A132 concepts
A Clustering ModelThe supplied source pack does not define PCA or variance maximization.A First Look at a Neural NetworkAdvanced deep learning combines tensor-based data representation, tensor operations, and…Abstract Base Classes and InterfacesPolymorphism allows a subtype to be treated as an instance of its parent type, enabling f…Abstraction of low-level detailsThe characteristic of high-level languages where the programmer does not need to manage l…Accessing Attributes and MethodsAn object bundles data (attributes) and behavior (methods) into a single, organized unit.Accessing Dictionary ValuesA dictionary is a mapping between keys and values, not a sequence indexed by position lik…Accessing Dictionary Values with the Index OperatorA for loop over a dictionary iterates through keys; to filter by value, use the index ope…Accessing list elements with indexingA list is a sequence of values that can contain any data type, unlike strings which conta…
B72 concepts
BackpropagationTensors provide the multi-dimensional representations used by neural networks.Backward EliminationGreedy selection evaluates feature subsets through the learning algorithm rather than sep…Backward-view temporal-difference learningThe on-line λ-return algorithm motivates this topic because it combines strong performanc…Balancing Exploration and Exploitation with Upper-Confidence-Bound Action SelectionUCB combines an estimated action value with an uncertainty bonus.Base Hypothesis ClassThe base class B provides the individual hypotheses used as building blocks.Basic for loop syntaxLoops scan through data by following a three-part structure: initialize a tracking variab…Basic if StatementsAn if-else statement creates two mutually exclusive branches: one executes if the conditi…Basic Mathematical FunctionsPython's trigonometric functions (sin, cos, tan) take arguments in radians, not degrees
C209 concepts
CalculusBackpropagation is an algorithm for computing the gradient values of a neural network.Calling a FunctionA function call transfers execution to the function's code block and returns to the calle…Calling Built-in FunctionsArguments are values passed to a function during a call; parameters are variables inside…Calling Functions with Multiple ArgumentsFunctions are reusable pieces of programs. They allow you to give a name to a block of st…Calling Methods on ObjectsThe self parameter is the first parameter in every class method and refers to the instanc…Capturing Groups and BackreferencesGreedy quantifiers expand to match the last occurrence of a pattern; non-greedy quantifie…Carathéodory's TheoremThe compressed object is a subset of training points, not the weight vector itself.Catching Exceptions with try and except BlocksThe Python interpreter recovers from errors and returns a prompt; a script terminates imm…
D230 concepts
Data Cleaning and Normalization in Large ArchivesMapping tables unify changing email addresses and multiple domain names into single canon…Data CompressionUnsupervised learning finds useful transformations of input data without target values.Data Consistency Across Distributed SystemsService-oriented architecture enables travel websites to integrate multiple independent s…Data Integrity and ConstraintsA uniqueness constraint ensures all values in a column are unique by using a special inde…Data Matrix Representation in PCAMatrix A uses X transposed X and has dimensions determined by the original features.Data Normalization and Compression TechniquesThe three-database pipeline consists of content.sqlite (raw, uncompressed), gmodel.py (tr…Data Persistence and Program StateMain memory (CPU and RAM) is where programs execute and store data while running, but it…Data Pipeline Design and Best PracticesA geospatial application pipeline connects input data, a geocoding API, a database, and a…
E109 concepts
Effective SizeA class with small effective size enjoys the uniform convergence property.Efficient Action-Value EstimationAn average can be updated incrementally rather than recomputed from all previous rewards.Efficient Implementation of NN RuleApproximate nearest neighbor search improves performance by allowing a bounded approximat…Efficient learnability in the realizable caseA Boolean conjunction maps X = {0, 1}^n to Y = {0, 1}.Eigenvalue DecompositionNon-invertibility can arise when training instances do not span the entire space of R^d.EigenvaluesA symmetric matrix is positive definite when every eigenvalue is positive.Eigenvectors and EigenvaluesMatrix A uses X transposed X and has dimensions determined by the original features.Element-wise ProductThe tensor dot operation combines entries in its input tensors.
F115 concepts
Feature ConstructionRBF networks are function approximators whose features are radial basis functions.Feature Construction for Linear Function ApproximationEach OrderN polynomial basis function multiplies one powered term for every state variabl…Feature EngineeringA machine learning problem is defined by its inputs, predicted outputs, and problem type.Feature extractionPreprocessing changes raw data into numerical forms that neural networks can use.Feature Manipulation and NormalizationFeature transformations should be selected according to the property that needs to change.Feature Mappings for Polynomial ClassifiersCompression keeps a smaller representation from which a zero-training-loss predictor can…Feature Maps and FiltersConvolution focuses on local patches rather than treating the entire image as one undivid…Feature Maps in Convolutional Neural NetworksMax pooling replaces each local window with its maximum value.
G71 concepts
Game-Playing Programs and Lookahead SearchHeuristic search decides how much of the possible game tree to examine.General Books on Reinforcement LearningUse the purpose of your reading to choose among the listed resource categories.GeneralizationOverfitting occurs when a hypothesis fits the training data too well but performs poorly…Generalization and Function Approximation in Reinforcement LearningA policy can be represented by a parameterized function whose parameters form the weight…Generalization and Learnabilityϵ-representativeness describes a condition on a training set S relative to Z, H, ℓ, and D.Generalization and Learning GuaranteesThe No-Free-Lunch Theorem rules out a learner that succeeds on every learning task.Generalization BoundsMargin separation supplies the condition for the Perceptron convergence guarantee.Generalization Bounds for Linear PredictorsHard-SVM's output w_S is defined by Equation (26.19) and satisfies L_S(w_S) = 0 under the…
H84 concepts
Habit Learning and Goal-Directed BehaviorGoal-directed and habitual behavior rely on different, though not necessarily exclusive,…Habitual and Goal-Directed Processes in the BrainModel-free and model-based reinforcement learning provide a distinction for studying brai…Habitual BehaviorThe experiment changes reward value after learning and measures whether behavior adjusts.Halfspace HypothesesThe same dot product ⟨w, x⟩ can be interpreted probabilistically by logistic regression o…Halfspace LearningSurrogate losses replace other losses for purposes such as computational convenience.HalfspacesThe base class B provides the individual hypotheses used as building blocks.Handling API Rate Limits and ThrottlingSQLite serves as a local cache to store geocoding results, preventing redundant API calls…Handling Binary Data and Encoding in PythonA socket connection to port 80 establishes a reliable communication channel with a web se…
I162 concepts
ID3 Decision Tree LearningDecision tree learning searches for a tree that minimizes the relevant bound, but solving…if-else StatementsThe if statement checks a condition and executes indented code only if that condition is…Image ClassificationThe convnet progressively exchanges spatial detail for deeper feature representations.Image Classification with Deep LearningA pretrained network is a saved network trained previously on a large dataset, such as Im…Image Editing with Concept VectorsA VAE combines an encoder, a sampling step, and a decoder.IMDB and Reuters Text Classification ExamplesOne-hot encoding is a basic method for turning tokens into vectors.Immediate and Future RewardsDiscounting lets an agent compare rewards that arrive at different times.Immutability and Tuple PropertiesPython compares tuples element-by-element from left to right, stopping at the first index…
J10 concepts
Jacobian MatrixBackpropagation calculates the gradient of a loss with respect to network weights for an…JavaScript for Web VisualizationA geospatial application pipeline connects input data, a geocoding API, a database, and a…Jensen's InequalityGradient Descent convergence is analyzed here for convex-Lipschitz functions.JOIN Syntax and FundamentalsMany-to-many relationships require three tables: two entity tables and one junction table…Joins: Combining Data from Multiple TablesSQL uses a single equal sign (=) for equality testing in WHERE clauses, not the double eq…JSON and XML: Data Formats for Web ServicesA web service is a set of services in an application's API that are made available over t…JSON Syntax and StructureXML uses tags and attributes; JSON uses curly braces and key-value pairs to represent the…JSON: A Lightweight Data FormatAn API is an application-to-application contract that publishes rules for accessing servi…
K17 concepts
k Nearest Neighbors AlgorithmThe k-NN rule maps a training sample and a chosen k to a label for each point under consi…k-Means and Other Cost Minimization ClusteringsThe objective function and the iterative algorithm are related but not identical ideas.k-Means ClusteringDictionary learning creates a feature vocabulary for data that may not have an obvious vo…k-NN Classificationk-NN regression predicts a real-valued target by combining the targets of the k nearest n…Kamin BlockingThe Rescorla-Wagner model links learning to surprise.KerasThe convnet progressively exchanges spatial detail for deeper feature representations.Keras and Deep Learning FrameworkPart 1 is a staged introduction rather than a single isolated topic.Keras datasetsMNIST is a classic handwritten-digit classification dataset.
L128 concepts
Lambda Forms and List ComprehensionsA lambda statement creates an anonymous function object with one parameter and one expres…Lambda FunctionsList comprehensions are a concise syntax for creating a new list by transforming or filte…Lambda Functions and the key ParameterThe DSU pattern transforms custom sorting into three simple, clear phases: decorate (add…Large Margin ClassificationSoft-SVM combines labeled training pairs and a positive λ parameter in an optimization pr…Large State Spaces and Function ApproximationUCB can perform well on bandit problems, but that success does not make extension to gene…Latent RepresentationsA latent space of images is a low-dimensional vector space whose points can be mapped to…Latent Space SamplingGANs can generate new data by learning statistical structure from training data.Launching an AWS EC2 GPU InstanceEC2 asks about creating new connection keys or reusing existing keys at the end of the la…
M132 concepts
Machine Code and Binary: What the CPU Actually UnderstandsThe CPU is the part of the computer built to obsessively ask 'What is next?' and determin…Machine Language and Binary RepresentationA compiler translates an entire program from high-level source code to machine language i…Machine LearningDeep learning is a subset of machine learning.Machine Learning Data TerminologyA class is a category in a classification problem.Machine Learning DatasetsData provides the material from which deep-learning systems learn.Machine Learning EssentialsUnsupervised learning finds useful transformations of input data without target values.Machine Learning FoundationsThe basic prerequisite is Python programming experience.Machine learning model capacityOptimization and generalization measure different kinds of model performance.
N92 concepts
n-step action-value backupsn-step Q(σ) unifies Sarsa and tree backup by allowing sampling and expectation to be sele…n-step Action-Value Backups with Q(σ)ε-greedy behavior is defined relative to the current Q-values of the target policy.n-Step BackupsThe full return is the complete discounted reward sequence through episode termination.n-Step BootstrappingThe differential n-step return is G(n)t = R̄ + V̄(S(t+n)) − V̄(S(t)).n-step Expected Sarsan-step Q(σ) is a unifying framework for action-value backups.n-step MethodsOff-policy learning separates the policy collecting experience from the policy being lear…n-Step Methods for Reinforcement Learningn-step semi-gradient Sarsa joins a semi-gradient Sarsa control method with n-step bootstr…n-step Returns and the λ-returnThe forward view of eligibility traces connects eligibility-trace ideas with n-step retur…
O102 concepts
OAuth 2.0 Authorization Code FlowOAuth libraries are free, pre-built tools that handle the complexity of the OAuth 2.0 pro…OAuth and Token-Based AuthenticationAPI keys are the mechanism vendors use to identify users and monitor their service consum…Object Attributes and MethodsObjects have a complete lifecycle: creation (via __init__), active use, and destruction (…Object Initialization and CleanupSpecial methods enable custom classes to mimic built-in type behaviors through double-und…Object Instantiation and Class CallsClass methods have only one specific difference from ordinary functions - they must have…Object-Oriented Design PrinciplesFields are ordinary variables bound to class or object namespaces, scoped to their contex…Object-oriented programmingA programming paradigm where the program is constructed around objects that integrate dat…Object-Oriented Programming BasicsProcedure-oriented programming organizes code around reusable functions; object-oriented…
P150 concepts
PAC LearnabilityShattering means realizing every possible 0/1 labeling on a chosen set.PAC LearningRealizability demands perfect agreement between some hypothesis in H and a target labelin…PAC Learning and Sample ComplexityUniform convergence connects a finite i.i.d. sample with representativeness of an underly…PAC Learning ModelOnline learning has no separate training phase followed by a separate prediction phase.PAC-Bayes BoundsThe PAC-Bayes bound can be converted into a learning rule.PAC-Bayes Bounds and Measure ConcentrationPAC-Bayes bounds define a hierarchy over a hypothesis class H.Parameter Tuningk-Fold Cross Validation helps estimate true error without setting aside a permanently unu…Parameterized Function ApproximationContinuing cases motivate the average reward formulation.
Q15 concepts
Q-learning: Off-policy TD ControlThe cliff-walking task separates the shortest optimal route from the safer route under ex…Q-value estimationOff-policy n-step Q(σ) separates the policy that generates experience from the policy who…Quantifiers and Repetition PatternsThe backslash (\) is the escape character that converts special regex characters into lit…Quantifiers: Matching Multiple CharactersThe period (.) in a regular expression is a wildcard that matches any single character—le…Query Optimization and Performance TuningAn index is extra information stored by a database to enable faster lookups on a specific…Querying and Analyzing Data in SQLitespider.py systematically crawls web pages and stores them in a local database, recording…Querying and Retrieving Data with SELECTAuto-generated primary keys shift the responsibility for ID management from the applicati…Querying Data from SQLite with SELECT StatementsUse the Database Browser for SQLite to verify that your Python programs are correctly rea…
R160 concepts
Rademacher ComplexityThe chaining technique uses covering numbers to bound Rademacher complexity.Rademacher Complexity and Generalization BoundsRademacher complexity is a measure of the complexity of a set of functions or vectors.Rademacher Complexity for Linear PredictorsHard-SVM's output w_S is defined by Equation (26.19) and satisfies L_S(w_S) = 0 under the…Rademacher Complexity of Linear ClassesThe H1 proof reduces a Rademacher-complexity calculation to a finite-set problem.Raising and catching custom exceptionsThe else block in exception handling runs only when the try block succeeds without raisin…Raising and Handling ExceptionsCustom exceptions are user-defined classes that inherit from Exception, enabling you to r…Raising ExceptionsThe try..except statement separates normal code (try block) from error-handling code (exc…Random ProjectionThe lemma gives a probabilistic guarantee that distances between vectors can be preserved…
S253 concepts
Sample ComplexityRegression loss functions measure more than whether a prediction is wrong: they quantify…Sample Complexity of Finite Hypothesis ClassesThree conjunctions connected by OR define a 3-term DNF.Sample Complexity of Neural NetworksVC dimension is a measure of hypothesis-class capacity based on shattering.Sample ModelPlanning uses model-generated experience, while learning uses experience from the real en…Sample Models in BlackjackThe key distinction is whether the model exposes the full probability description or only…Sample Size FlexibilityThe two notions share the same competitiveness requirement.Sample-Average Action-Value EstimationA sample average is a natural estimate of an action value.Sample-Average Action-Value MethodsInitial estimates affect action-value methods because they provide the starting values us…
T171 concepts
Tabular n-step TD algorithmThe semi-gradient n-step TD algorithm is the function-approximation extension of tabular…Tabular Solution Methods in Reinforcement LearningBandit problems are the single-state special case of reinforcement learning.Tabular TD(0) for Estimating Value FunctionsThe TD error is the difference between the current estimate V(S_t) and the one-step estim…TD Control MethodsThe cliff-walking task requires safe movement from S to a goal in a grid world.TD Error and Dopamine Neuron ActivityTD error, denoted δt, is examined as a quantity that changes over the course of learning.TD Error ConceptThe hypothesis is about an error between old and new estimates of expected future reward.TD ErrorsThe reward prediction error hypothesis links dopamine neuron activity with reward predict…TD Prediction MethodsThe value of n is an important performance setting in n-step TD methods.
U236 concepts
Uncertainty in EnvironmentGoal-directed agents pursue explicit goals through sensing and action.Understand Boolean ExpressionsAlternative execution uses if-else to run one of two code blocks based on whether a condi…Understand Comparison OperatorsAlternative execution uses if-else to run one of two code blocks based on whether a condi…Understanding __init__ and the Constructorsuper() is a special syntax that calls a method from the parent class. In the context of…Understanding Angle Measurement SystemsPython's trigonometric functions (sin, cos, tan) take arguments in radians, not degreesUnderstanding APIs: Contracts Between ApplicationsAn API is a published contract between applications that specifies the exact rules for re…Understanding Artificial IntelligenceClassical programming starts with rules written by humans and uses them to process data.Understanding Attributes and MethodsA class is a template that defines what data and code each object will have; the class ke…
V68 concepts
ValidationApproximation error measures the gap between the best hypothesis in a class and the true…Validation and Model EvaluationThe usefulness of a learnability definition depends on the goal for which it is being use…Validation TechniquesA model-selection curve compares training and validation error across model complexity.Value BackupsBackward focusing directs planning from a changed value toward states that may depend on…Value Estimates and Backup MethodsHeuristic search focuses on the current state and its likely successors.Value Estimates in Reinforcement Learningq∗(a) denotes the true value of action a.Value Estimation Across Episode HorizonsThe h-truncated λ-return method expands its available information one horizon at a time.Value Estimation in Reinforcement LearningA reward signal describes immediate desirability, while a value function describes long-t…
W157 concepts
Watson's Daily-Double Wagering StrategyWatson evaluated wagers as actions rather than judging them only by their point amounts.Watson's Question Answering and Game-Playing ArchitectureWatson treated Daily-Double wagering as a decision under uncertainty rather than as a fix…Weak LearnabilityA 3-piece classifier operates on the real line and is specified by two real thresholds th…Weak LearnersBoosting provides a way to manage the tradeoff between approximation error and estimation…Web Crawling and Data Collection with spider.pyPageRank is computed by running sprank.py, which iteratively calculates importance scores…Web Crawling with spider.pyVisualizing a network graph requires running spjson.py to convert your PageRank database…Web Scraping Basicscurl and wget are command-line tools for retrieving files from the web on Unix-like syste…Web Scraping Ethics and Best PracticesBeautifulSoup is a Python library designed to parse real-world HTML, which is often malfo…
X8 concepts
Xception ArchitectureNormalization makes samples more similar by centering and scaling their values, which can…XML Attributes and Text ContentXML documents are organized as tree structures with a single root element containing all…XML Basics and StructureXML uses tags and attributes; JSON uses curly braces and key-value pairs to represent the…XML Document Structure and the Root ElementAn XML element is a complete unit consisting of an opening tag, content, and a closing ta…XML Fundamentals and Use CasesJSON has become the industry standard for data exchange because its structure maps direct…XML Structure and SyntaxTriple single quotes (''') and triple double quotes (""") both create multi-line strings…XML Validation and SchemaAn XML element is a complete unit consisting of an opening tag, content, and a closing ta…XML: Structuring Complex DataAn API is an application-to-application contract that publishes rules for accessing servi…