К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Generative AI Part 1 · LearnSpace
Назад в каталог
courseraАнализ данных

Generative AI Part 1

Курс от Northeastern University
Средний≈ 25.3 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

Introduces the theoretical foundations and advanced concepts of neural networks, generative models, transformers, and large language models. Students will explore how these AI systems create new data, process information, and learn through feedback, while analyzing their applications across various fields. The course emphasizes key principles in model building, optimization, and real-world generative AI use cases.

Навыки, которые вы освоите

Generative Model ArchitecturesModel OptimizationRecurrent Neural Networks (RNNs)Model TrainingGenerative AIArtificial Neural NetworksConvolutional Neural NetworksDeep LearningBayesian NetworkProbability DistributionProbabilityStatistical ModelingStatistical MethodsModel EvaluationLarge Language Modeling

Программа курса

7 модулей · 184 учебных материалов

01Foundations of Neural Networks and Optimization25 материалов

Getting Started

Course IntroductionЧтениеMeet Your FacultyЧтениеSyllabus - Generative AI Part 1ЧтениеRecommended Prior KnowledgeЧтение

Учитесь у экспертов

Ramin Mohammadi

Преподаватель курса

Generative AI Part 1
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 25.3 ч

7 модулей

Язык: Английский

Часть программы вашего университета
Academic IntegrityЧтение

Lesson 1: Neural Networks

Neural Networks Part 1: PerceptronВидеоPerceptron In-DepthЧтениеNeural Network BreakdownЧтениеNeural Network StructureЧтениеNeural Networks Part 2: How Neural Networks LearnВидеоHow Neural Networks Learn: Deep DiveЧтениеNeural Networks Part 3: Back PropagationВидеоBackpropagation & SGDЧтениеModule 1- Assess Your Learning 1ЗаданиеModule OverviewЧтение

Lesson 2: Optimization Techniques

Optimization Technique Overview Part 1ВидеоMatricesЧтениеOptimization Technique Overview Part 2ВидеоNewton's MethodsЧтениеQuasi-Newton MethodsЧтениеOptimization Technique Overview Part 3ВидеоRoot-Mean-Square PropagationЧтениеAdaptive Moment EstimationЧтениеModule 1- Assess Your Learning 2Задание

Module Wrap-Up

Module Wrap-UpЧтение
02Regularization and Generalization Techniques23 материалов

Lesson 1: Regularization

Module OverviewЧтениеRegularization: Model Selection and ComplexityВидеоStein’s Unbiased Risk EstimatorЧтениеStein's LemmaЧтениеRegularizationЧтениеWhy Does Regularization Work?ЧтениеRegularization TechniquesВидеоEigen Decomposition and Singular Value DecompositionЧтениеUnderstanding the Search SpaceЧтениеRegularization TechniquesЧтениеBagging and Other Ensemble MethodsЧтениеModule 2- Assess Your Learning 1Задание

Lesson 2: Dropout

Introduction to DropoutВидеоDeep Dive Into DropoutЧтениеApplying Dropout to Linear RegressionЧтение

Lesson 3: Batch Normalization

Introduction to Batch NormalizationВидеоDeep Dive Into Batch NormalizationЧтениеInternal Covariate Shift and Domain AdaptationЧтениеNew Batch Normalization TechniquesЧтениеBatch Normalization EffectsЧтениеAlternatives to Batch NormalizationЧтение

Module Wrap-Up

Module Wrap-UpЧтение
03Convolutional Neural Networks38 материалов

Lesson 1: Convolutional Neural Networks (CNNs)

Module OverviewЧтениеIntroduction to Convolutional Neural NetworksЧтениеConvolutional Neural Networks Part 1: The First PrinciplesВидеоInvariance and EquivarianceЧтениеConvolutionЧтениеTranslationЧтениеKernel FlippingЧтениеConvolution vs. Cross-CorrelationЧтениеEdge DetectionЧтениеTypes of KernelsЧтениеParameter Sharing and FiltersЧтение

Lesson 2: Convolutional Neural Networks for 1D Inputs

Convolutional Neural Networks Part 2: 1D InputВидеоCNNs for 1D InputsЧтениеPaddingЧтениеStride, Kernel Size, and DilationЧтениеConvolutional Layers as Fully Connected LayersЧтение

Lesson 3: Convolution in Multidimensional Arrays

Convolutional Neural Networks Part 3: Multiple DimensionsВидеоConvolution in Multidimensional ArraysЧтениеArchitecture of Convolutional NNsЧтениеDownsamplingЧтениеUpsampling and LayersЧтение

Lesson 4: Putting It All Together

End-to-End Visualization of CNNsЧтениеConvolutional Neural Networks Part 4: BackpropagationВидеоBackpropagationЧтениеConvolutional LayersЧтениеKernel WeightsЧтениеConvolutional Neural Networks Part 5: PixelCNNВидео

Lesson 5: Regularization in CNNs

Recap on RegularizationЧтениеIdeas to Get Around the Optimization ProblemЧтениеLayer Normalization FormulasЧтениеFilter Response Normalization (FRN)ЧтениеNormalizer-Free NetworksЧтение Module 3- Assess Your Learning 2Задание

Lesson 6: Random Kernels

Why Random Kernels Learn Different ThingsЧтение

Module Wrap-Up

Module Wrap-UpЧтение
04Generative Models and Maximum Likelihood Estimation41 материалов

Lesson 1: Maximum Likelihood Learning

Module OverviewЧтениеIntro to Maximum Likelihood LearningВидеоLearning a Generative ModelЧтениеGoal of LearningЧтениеWhat is “Best?"ЧтениеLearning as Density EstimationЧтение

Lesson 2: Divergence Methods

Divergence Methods & Gradient DescentВидеоKullback-Leibler (KL-Divergence)ЧтениеDetour on KL-DivergenceЧтениеExpected Log-LikelihoodЧтениеMonte Carlo EstimationЧтениеExtending the MLE Principle to Autoregressive ModelsЧтениеMLE Learning: Gradient DescentЧтениеMLE Learning: Stochastic Gradient DescentЧтениеEmpirical Risk and OverfittingЧтение Module 4- Assess Your Learning 1Задание

Lesson 3: Representation

Representation Part 1: DistributionsВидеоLearning a Generative Model Part 2ЧтениеBasic Discrete DistributionsЧтениеStructure Through IndependenceЧтениеKey Notion: Conditional IndependenceЧтениеBayesian NetworksЧтение

Lesson 4: Autoregressive Models

Autoregressive Models General PrinciplesВидеоMotivating Example: MNISTЧтениеIntroduction to Autoregressive ModelsЧтениеFully Visible Sigmoid Belief Networks (FVSBN)ЧтениеNADE: Neural Autoregressive Density EstimationЧтениеAutoregressive Models ContinuedВидео

Module Wrap-Up

Module Wrap-UpЧтение
05Recurrent Neural Networks21 материалов

Lesson 1: Recurrent Neural Networks

Module OverviewЧтениеIntroduction to Recurrent Neural NetworksВидеоIntroduction to Recurrent Neural NetworksЧтениеDynamic SystemsЧтениеComputing Gradient in RNNsЧтениеTraining RNNsВидеоTraining an RNN Language ModelЧтениеProblems with RNNsЧтениеPotential Solutions to RNN IssuesЧтение Module 5- Assess Your Learning 1Задание

Lesson 2: Gated Recurrent Neural Networks

Long Short-Term MemoryВидеоGated RNNs and LSTMЧтениеGated Recurrent Unit (GRU)ВидеоGated Recurrent Unit: In-DepthЧтениеExtension of Residual Networks to RNNsЧтениеMotivationЧтение Module 5- Assess Your Learning 2

Lesson 3: Bidirectional RNNs

Intro to Bidirectional RNNsЧтениеMultilayer RNNsЧтение Module 5- Assess Your Learning 3Задание

Module Wrap-Up

Module Wrap-UpЧтение
06Sequence-to-Sequence Models and Attention Mechanism13 материалов

Lesson 1: Attention Mechanism In Seq2Seq

Module OverviewЧтениеMotivation for Attention MechanismЧтениеSequence to Sequence ModelsВидеоSeq2SeqЧтениеChallenges of Seq2SeqЧтение Module 6- Assess Your Learning 1Задание

Lesson 2: Sequence to Sequence Models In-Depth

Attention in Seq2Seq: Dynamic AttentionВидеоAttention MechanismЧтениеComputing Attention WeightsЧтениеAttention in Translation: DecodingВидеоDetailed Attention in Seq2Seq & DecodingЧтение Module 6- Assess Your Learning 2Задание

Module Wrap-Up

Module Wrap-UpЧтение
07Transformer Architecture23 материалов

Lesson 1: Exploring Transformers: Self-Attention

Module OverviewЧтениеTransformers Part 1: Applications and Key Query ValueВидеоKey, Query, Value & Self-AttentionЧтениеSelf-Attention As RoutingЧтениеComputing and Weighting ValuesЧтениеTransformers Part 2: Self-AttentionВидеоSelf-Attention in SummaryЧтение Module 7- Assess Your Learning 1Задание

Lesson 2: Structuring Transformer Inputs

Transformers Part 3: Position InformationВидеоPosition RepresentationЧтениеThe IntuitionЧтениеChanging Alpha Directly & Future MaskingЧтение Module 7- Assess Your Learning 2Задание

Lesson 3: Understanding Multihead Attention

Multihead AttentionЧтениеSequence Tensor FormЧтение Module 7- Assess Your Learning 3Задание

Lesson 4: Understanding Transformers

Transformer MechanismsЧтениеTypes of TransformersЧтениеDecoder Process with Cross-AttentionЧтениеDrawbacks of TransformersЧтение Module 7- Assess Your Learning 4Задание

Module Wrap-Up

Module Wrap-UpЧтениеCongratulations!Чтение
Module 2- Assess Your Learning 2Задание
Applications of CNNsЧтение
Residual Neural NetworksЧтение
Module 3- Assess Your Learning 1Задание
ExamplesЧтение
Naive BayesЧтение
Representation Part 2: Discriminative vs General ModelsВидео
Discriminative vs. Generative ModelsЧтение
Generative Models Are Still UsefulЧтение
Bayesian Networks vs. Neural ModelsЧтение
Module 4- Assess Your Learning 2Задание
General Discrete DistributionsЧтение
Real-Valued Neural Autoregressive Density-Estimator (RNADE)Чтение
Autoregressive Models vs. AutoencoderЧтение
Summary of Autoregressive ModelsЧтение
Module 4- Assess Your Learning 3Задание
Задание