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
Machine Learning with PyTorch and Scikit-Learn · LearnSpace
Назад в каталог
courseraАнализ данных

Machine Learning with PyTorch and Scikit-Learn

Курс от Packt
Средний≈ 43.2 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course offers a comprehensive exploration of machine learning and deep learning using PyTorch and Scikit-Learn. It provides clear explanations, visualizations, and practical examples to help learners build and deploy machine learning models. Ideal for Python developers, it covers the latest trends in deep learning, including GANs, reinforcement learning, and NLP with transformers. Packed with clear explanations, visualizations, and working examples, the course covers essential machine learning techniques in depth, along with two cutting-edge machine learning techniques: transformers and graph neural networks. This course is designed for developers and data scientists with a solid understanding of Python basics, calculus, and linear algebra. It is ideal for those looking to create practical machine learning applications using Scikit-Learn and PyTorch, and deepen their knowledge of advanced deep learning techniques. Throughout this course you will learn to: - Develop machine learning models using Scikit-Learn and PyTorch. - Implement neural networks and transformers for various data types. - Apply best practices for model evaluation and tuning. This course is based on material written by an expert author, bringing the depth of a book into a more engaging, interactive format. The core content is delivered through clear, structured text you can read at your own pace, supported by short videos and quizzes to highlight key ideas and test your understanding. By combining the strengths of book learning with interactive assessments, you get the best of both worlds: the depth and clarity of an author’s expertise, plus the flexibility to revisit, practice, and reinforce concepts whenever you need.

Навыки, которые вы освоите

PyTorch (Machine Learning Library)Scikit Learn (Machine Learning Library)Model EvaluationData PreprocessingMachine Learning AlgorithmsMachine LearningNatural Language ProcessingModel OptimizationArtificial Neural NetworksDimensionality ReductionGenerative Adversarial Networks (GANs)Model TrainingReinforcement LearningFeature EngineeringArtificial Intelligence and Machine Learning (AI/ML)Applied Machine LearningPython ProgrammingDeep LearningPandas (Python Package)Generative AI

Программа курса

19 модулей · 209 учебных материалов

01Giving Computers the Ability to Learn from Data8 материалов
Course OverviewВидеоModule OverviewВидеоIntroductionЧтениеSolving Interactive Problems with Reinforcement LearningЧтение

Учитесь у экспертов

Packt - Course Instructors

Преподаватель курса

Machine Learning with PyTorch and Scikit-Learn
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

≈ 43.2 ч

19 модулей

Язык: Английский

Субтитры: Арабский, Французский, Итальянский, Бразильский португальский, Корейский, Немецкий, Испанский, Японский, Венгерский

Часть программы вашего университета
Introduction to the Basic Terminology and NotationsЧтение
A Roadmap for Building Machine Learning SystemsЧтение
Using Python for Machine LearningЧтение
Knowledge CheckЗадание
02Training Simple Machine Learning Algorithms for Classification11 материалов
OverviewВидеоIntroductionЧтениеThe Perceptron Learning RuleЧтениеImplementing a Perceptron Learning Algorithm in PythonЧтениеTraining a Perceptron Model on the Iris DatasetЧтениеAdaptive Linear Neurons and the Convergence of LearningЧтениеImplementing Adaline in PythonЧтениеImproving Gradient Descent Through Feature ScalingЧтениеImplementing a Perceptron from Scratch in PythonЛабораторнаяPerceptron Lab AutograderПрограммированиеKnowledge checkЗадание
03A Tour of Machine Learning Classifiers Using Scikit-Learn15 материалов
OverviewВидеоIntroductionЧтениеModeling Class Probabilities Via Logistic RegressionЧтениеLearning the Model Weights via the Logistic Loss FunctionЧтениеConverting an Adaline Implementation Into an Algorithm for Logistic RegressionЧтениеTraining a Logistic Regression Model with Scikit-LearnЧтениеTackling Overfitting via RegularizationЧтениеMaximum Margin Classification with Support Vector MachinesЧтениеSolving Nonlinear Problems Using a Kernel SVMЧтениеDecision Tree LearningЧтениеBuilding a Decision TreeЧтениеK-Nearest Neighbours A Lazy Learning AlgorithmЧтениеDecision Tree LabЛабораторнаяDecision Tree Lab ПрограммированиеKnowledge checkЗадание
04Building Good Training Datasets: Data Preprocessing13 материалов
OverviewВидеоIntroductionЧтениеUnderstanding the scikit-learn Estimator APIЧтениеPerforming One-Hot Encoding on Nominal FeaturesЧтениеPartitioning a Dataset Into Separate Training and Test DatasetsЧтениеBringing Features Onto the Same ScaleЧтениеSelecting Meaningful FeaturesЧтениеSparse Solutions With L1 RegularizationЧтениеSequential Feature Selection AlgorithmsЧтениеAssessing Feature Importance with Random forestsЧтениеHands-On: Random Forests for Feature ImportanceЛабораторнаяGraded Assignment: Random Forests for Feature ImportanceПрограммированиеKnowledge checkЗадание
05Compressing Data Via Dimensionality Reduction9 материалов
OverviewВидеоIntroductionЧтениеExtracting the Principal Components Step by StepЧтениеFeature TransformationЧтениеPrincipal Component Analysis in scikit-learnЧтениеSupervised Data Compression via Linear Discriminant AnalysisЧтениеSelecting Linear Discriminants for the New Feature SubspaceЧтениеNonlinear Dimensionality Reduction and VisualizationЧтениеKnowledge checkЗадание
06Learning Best Practices For Model Evaluation And Hyperparameter Tuning12 материалов
OverviewВидеоIntroductionЧтениеUsing K-Fold Cross-Validation to Assess Model PerformanceЧтениеEstimating generalization performanceЧтениеAddressing Over- And Underfitting With Validation CurvesЧтениеMore Resource-Efficient Hyperparameter Search With Successive HalvingЧтениеLooking at Different Performance Evaluation MetricsЧтениеPlotting a Receiver Operating CharacteristicЧтениеDealing With Class ImbalanceЧтениеHands-on: Performance Evaluation Metrics labЛабораторнаяPerformance Evaluation Metrics graded assignmentПрограммированиеKnowledge checkЗадание
07Combining Different Models For Ensemble Learning11 материалов
OverviewВидеоIntroductionЧтениеCombining Classifiers Via Majority VoteЧтениеUsing the Majority Voting Principle to Make PredictionsЧтениеEvaluating and Tuning the Ensemble ClassifierЧтениеBagging Building An Ensemble Of Classifiers From Bootstrap SamplesЧтениеLeveraging Weak Learners Via Adaptive BoostingЧтениеApplying AdaBoost Using scikit-learnЧтениеGradient Boosting Training An Ensemble Based On Loss GradientsЧтениеExplaining the Gradient Boosting Algorithm for ClassificationЧтениеKnowledge checkЗадание
08Applying Machine Learning to Sentiment Analysis11 материалов
OverviewВидеоIntroductionЧтениеIntroducing the Bag-Of-Words ModelЧтениеAssessing Word Relevancy Via Term Frequency-Inverse Document FrequencyЧтениеCleaning Text DataЧтениеTraining a Logistic Regression Model for Document ClassificationЧтениеWorking with Bigger Data Online Algorithms and Out-of-Core LearningЧтениеTopic Modeling with Latent Dirichlet AllocationЧтениеHands-on: Cleaning text and building a bag-of-wordsЛабораторнаяAssignment: Cleaning text and building a bag-of-wordsПрограммированиеKnowledge checkЗадание
09Predicting Continuous Target Variables With Regression Analysis8 материалов
OverviewВидеоIntroductionЧтениеLooking at Relationships Using a Correlation MatrixЧтениеEstimating the Coefficient of a Regression Model via scikit-learnЧтениеUsing Regularized Methods for RegressionЧтениеDealing With Nonlinear Relationships Using Random ForestsЧтениеRandom Forest RegressionЧтениеKnowledge checkЗадание
10Working with Unlabeled Data - Clustering Analysis7 материалов
OverviewВидеоIntroductionЧтениеA smarter way of placing the initial cluster centroids using k-means++ЧтениеUsing the elbow method to find the optimal number of clustersЧтениеGrouping clusters in a bottom-up fashionЧтениеAttaching dendrograms to a heat mapЧтениеKnowledge checkЗадание
11Implementing a Multilayer Artificial Neural Network from Scratch10 материалов
OverviewВидеоIntroductionЧтениеIntroducing the Multilayer Neural Network ArchitectureЧтениеActivating a Neural Network via Forward PropagationЧтениеClassifying Handwritten DigitsЧтениеImplementing a Multilayer PerceptronЧтениеCoding the Neural Network Training LoopЧтениеEvaluating the Neural Network PerformanceЧтениеTraining Neural Networks Via BackpropagationЧтениеKnowledge checkЗадание
12Parallelizing Neural Network Training with PyTorch13 материалов
OverviewВидеоIntroductionЧтениеFirst Steps with PyTorchЧтениеSplit, Stack, And Concatenate TensorsЧтениеShuffle, Batch, and RepeatЧтениеFetching Available Datasets From the torchvision.datasets LibraryЧтениеBuilding an NN Model in PyTorchЧтениеModel Training via the torch.nn and torch.optim ModulesЧтениеSaving and Reloading the Trained ModelЧтениеEstimating Class Probabilities in Multiclass Classification via the Softmax FunctionЧтениеHands-On: The basics of PyTorchЛабораторнаяAssignment: the basics of PyTorchПрограммированиеKnowledge checkЗадание
13Going Deeper: The Mechanics of PyTorch11 материалов
OverviewВидеоIntroductionЧтениеComputing Gradients via Automatic DifferentiationЧтениеSimplifying Implementations of Common Architectures via the torch.nn ModuleЧтениеSolving an XOR Classification ProblemЧтениеMaking Model Building More Flexible With nn.ModuleЧтениеProject One Predicting the Fuel Efficiency of a CarЧтениеTraining a DNN Regression ModelЧтениеHigher-Level PyTorch APIs A Short Introduction to PyTorch-LightningЧтениеTraining the Model Using the PyTorch Lightning Trainer ClassЧтениеKnowledge checkЗадание
14Classifying Images with Deep Convolutional Neural Networks12 материалов
OverviewВидеоIntroductionЧтениеPadding inputs to control the size of the output feature mapsЧтениеPerforming a discrete convolution in 2DЧтениеSubsampling layersЧтениеWorking with multiple input or color channelsЧтениеRegularizing an NN with L2 regularization and dropoutЧтениеLoss functions for classificationЧтениеThe multilayer CNN architectureЧтениеLoading the CelebA datasetЧтениеTraining a CNN smile classifierЧтениеKnowledge checkЗадание
15Modeling Sequential Data Using Recurrent Neural Networks9 материалов
OverviewВидеоIntroductionЧтениеComputing activations in an RNNЧтениеThe challenges of learning long-range interactionsЧтениеProject one - predicting the sentiment of IMDb movie reviewsЧтениеBuilding an RNN modelЧтениеProject two - character-level language modeling in PyTorchЧтениеBuilding a character-level RNN modelЧтениеKnowledge checkЗадание
16Transformers Improving Natural Language Processing With Attention Mechanisms16 материалов
OverviewВидеоIntroductionЧтениеGenerating Outputs from Context VectorsЧтениеIntroducing the Self-Attention MechanismЧтениеParameterizing the Self-Attention Mechanism Scaled Dot-Product AttentionЧтениеAttention Is All We Need: Introducing the Original Transformer ArchitectureЧтениеLearning a Language Model Decoder and Masked Multi-Head AttentionЧтениеBuilding Large-Scale Language Models by Leveraging Unlabeled DataЧтениеLeveraging Unlabeled Data with GPTЧтениеUsing GPT-2 to Generate New TextЧтениеBidirectional Pre-Training with BERTЧтениеThe Best of Both Worlds BARTЧтениеFine-Tuning a BERT Model in PyTorchЧтениеLoading and Fine-Tuning a Pre-Trained BERT ModelЧтениеFine-Tuning a Transformer More Conveniently Using the Trainer APIЧтениеKnowledge checkЗадание
17Generative Adversarial Networks for Synthesizing New Data10 материалов
OverviewВидеоIntroductionЧтениеGenerative models for synthesizing new dataЧтениеTraining GAN models on Google ColabЧтениеDefining the training datasetЧтениеTransposed convolutionЧтениеImplementing the generator and discriminatorЧтениеDissimilarity measures between two distributionsЧтениеUsing EM distance in practice for GANsЧтениеKnowledge checkЗадание
18Graph Neural Networks for Capturing Dependencies in Graph Structured Data9 материалов
OverviewВидеоIntroductionЧтениеImplementing a Basic Graph ConvolutionЧтениеImplementing a GNN in PyTorch from ScratchЧтениеBatch Is a List of Dictionaries Each Containing the Representation and Label of a GraphЧтениеImplementing a GNN Using the PyTorch Geometric LibraryЧтениеOther GNN Layers and Recent DevelopmentsЧтениеPoolingЧтениеKnowledge checkЗадание
19Reinforcement Learning for Decision Making in Complex Environments14 материалов
OverviewВидеоIntroductionЧтениеDefining the agent-environment interface of a reinforcement learning systemЧтениеVisualization of a Markov processЧтениеValue FunctionЧтениеDynamic programming using the Bellman equationЧтениеDynamic programmingЧтениеValue iterationЧтениеTemporal difference learningЧтениеOff-policy TD control (Q-learning)ЧтениеImplementing the grid world environment in OpenAI GymЧтениеSolving the grid world problem with Q-learningЧтениеTraining a DQN model according to the Q-learning algorithmЧтениеImplementing a deep Q-learning algorithmЧтение