Skip to content
AI360Xpert
Learning Paths

Zero To Ai

A comprehensive guide for Zero To Ai

""1PROGRAMMING & SOFTWARE ENGINEERING BASICS2MATHEMATICS FOR MACHINE LEARNING3DATA ENGINEERING & PREPROCESSING4CLASSICAL MACHINE LEARNING5DEEP LEARNING FOUNDATIONS6COMPUTER VISION (CV)7NATURAL LANGUAGE PROCESSING (NLP)8REINFORCEMENT LEARNING (RL)9MLOPS, CLOUD, AND DEPLOYMENT10AI ETHICS, SAFETY, AND ALIGNMENTZero To AiDevelopment Environment SetupTerminal and CommandLineBashShell ScriptingFile NavigationEnvironment ManagementCondapipVirtual EnvironmentsvenvIDEs and ToolingVS CodeJupyter NotebooksExtensionsIntroduction to ProgrammingBasic PythonVariablesLoopsConditionalsData TypesFunctionsAdvanced PythonOOPDecoratorsGeneratorsError HandlingList ComprehensionsSoftware Engineering PracticesGit and VersionControlBranchingMergingPull RequestsGitHub ActionsData Structures &AlgorithmsBig O NotationTreesGraphsHash TablesAPIs and WebInteractionREST APIsHTTP RequestsWeb Scraping withBeautifulSoupLinear AlgebraVectors and MatricesOperationsDot ProductDeterminantsMatrix MultiplicationAdvanced LinearAlgebraEigenvectorsEigenvaluesSVDPCA MathematicsCalculusDifferential CalculusDerivativesChain RulePartial DerivativesGradientsOptimizationGradient DescentConvexityHessian MatrixJacobiansProbability and StatisticsProbability TheoryDistributionsBayes' TheoremRandom VariablesExpected ValueStatistical MethodsHypothesis TestingP-valuesA/B TestingConfidence IntervalsData Collection and StorageRelational DatabasesSQL QueriesJoinsAggregationsNormalizationNoSQL DatabasesMongoDBKey-Value StoresDocument StoresBig Data EcosystemsHadoopApache SparkKafkaData Manipulation and AnalysisNumPyN-dimensional ArraysBroadcastingVectorizationIndexingPandasDataFramesSeriesGroupByMergingPivot TablesData CleaningHandling MissingValuesOutlier DetectionImputationScalingData Visualization and EDAStatic VisualizationMatplotlibSeabornPlotsDistributionsCorrelationsInteractiveVisualizationPlotlyStreamlitDashBokehExploratory DataAnalysisFeature SelectionFeature EngineeringProfilingSupervised Learning: Regression and ClassificationLinear ModelsLinear RegressionLogistic RegressionCost FunctionsSupport VectorMachinesKernelsMargin MaximizationHyperplanesTree-Based ModelsDecision TreesRandom ForestsGradient BoostingXGBoostLightGBMProbabilistic andInstance-BasedNaive BayesK-Nearest NeighborsDistance MetricsUnsupervised LearningClustering AlgorithmsK-MeansHierarchicalClusteringDBSCANSilhouette ScoreDimensionalityReductionPCAt-SNEUMAPAutoencodersAssociation RuleLearningAprioriEclatFP-GrowthModel Evaluation and SelectionClassification MetricsAccuracyPrecisionRecallF1-ScoreROC-AUCConfusion MatrixRegression MetricsRMSEMAER-SquaredAdjusted R-SquaredCross-ValidationK-FoldStratified K-FoldGrid SearchRandom SearchOptunaArtificial Neural Networks (ANNs)Network ArchitectureNeuronsHidden LayersWeightsBiasesFeedforwardActivation FunctionsSigmoidReLULeaky ReLUTanhSoftmaxOptimization andRegularizationLoss FunctionsBackpropagationAdamSGDDropoutBatch NormalizationDeep Learning FrameworksPyTorchTensorsAutogradnn.ModuleDataLoadersCustom DatasetsTensorFlow and KerasComputational GraphsModel SubclassingCallbacksTensorBoardHardware AccelerationCUDAcuDNNGPUsTPUsMixed PrecisionTrainingImage Processing FundamentalsCore TechniquesFilteringEdge DetectionColor SpacesMorphologicalOperationsTraditional ComputerVisionOpenCVSIFTSURFHOGConvolutional Neural Networks (CNNs)ArchitectureComponentsConvolutional LayersPoolingStridesPaddingReceptive FieldsLandmark ArchitecturesResNetInceptionEfficientNetMobileNetAdvanced CV ApplicationsObject DetectionYOLOSSDFaster R-CNNRetinaNetImage SegmentationU-NetMask R-CNNSemantic vs. InstanceSegmentationGenerative VisionModelsGANsDiffusion ModelsStable DiffusionVision Transformers(ViT)Text Processing FundamentalsTraditional TechniquesTokenizationLemmatizationStemmingPOS TaggingRegexStatistical MethodsBag of WordsTF-IDFN-gramsStopwordsSequence Models and EmbeddingsWord EmbeddingsWord2VecGloVeFastTextContinuous Bag ofWordsRecurrent ModelsRNNsLSTMsGRUsSequence-to-SequenceAttention MechanismModern NLP and Large Language Models (LLMs)TransformerArchitectureSelf-AttentionMulti-Head AttentionEncoder-DecoderLeading ArchitecturesBERTGPT SeriesLLaMAMistralClaudeGeminiAdvanced LLMTechniquesPrompt EngineeringFine-TuningLoRAQLoRAPEFTRetrieval and AgentsRetrieval-AugmentedGeneration (RAG)Vector Databases(Pinecone, Chroma)LangChainLlamaIndexFundamentals of RLCore ConceptsAgentsEnvironmentsStatesActionsRewardsPoliciesMarkov DecisionProcessesMDPBellman EquationsValue FunctionsQ-ValuesValue and Policy MethodsTabular MethodsQ-LearningSARSADynamic ProgrammingMonte Carlo MethodsDeep ReinforcementLearningDQNDouble DQNPolicy GradientsAdvanced PolicyOptimizationPPOTRPOActor-Critic MethodsModern RL ApplicationsAI in Games andRoboticsAlphaGoMuZeroSim-to-Real TransferRL in Language ModelsRLHFRLAIFProximal PolicyOptimization forAlignmentCloud Computing and InfrastructureCloud PlatformsAWS SageMakerGCP Vertex AIAzure Machine LearningContainerization andOrchestrationDockerDocker ComposeKubernetesHelmModel Deployment and ServingServing FrameworksFastAPIFlaskTorchServeTriton InferenceServerRay ServeEdge and MobileDeploymentTensorFlow LiteONNX RuntimeCoreMLTensorRTMachine Learning Pipeline (MLOps)Experiment TrackingMLflowWeights & BiasesNeptuneDVCContinuous Integrationand MonitoringCI/CD for MLData DriftModel DecayEvidentlyEthics, Privacy, and FairnessBias and FairnessMitigating Model BiasDataset RepresentationAlgorithmic FairnessData Privacy andComplianceDifferential PrivacyFederated LearningGDPRHIPAAInterpretability and ExplainabilityExplainable AI (XAI)SHAPLIMEFeature ImportanceSaliency MapsMechanisticInterpretabilityCircuit DiscoveryFeature VisualizationSecurity and AlignmentAdversarial RobustnessPrompt InjectionModel PoisoningJailbreakingAdversarial TrainingAI AlignmentSuperalignmentSafety GuardrailsValue AlignmentConstitutional AI