Machine learning with PyTorch and Scikit-Learn : develop machine learning and deep learning models with Python
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Weitere Verfasser: | |
| Format: | Livre papier |
| Sprache: | Anglais |
| Veröffentlicht: |
Birmingham :
Packt Publishing
C 2022.
|
| Schlagworte: | |
| Autres localisations: | Voir dans le Sudoc |
| Edition sous un autre format: | • Machine Learning with PyTorch and Scikit-Learn, develop machine learning and deep learning models with Python, Sebastian Raschka, Yuxi (Hayden) Liu, Vahid Mirjalili, 2022, Birmingham, Packt Publishing, 978-18-0181-638-0 |
Inhaltsangabe:
- Chap. 1 : Giving computers the ability to learn from data
- Chap. 2 : Training simple machine learning algorithms for classification
- Chap. 3 : A tour of machine learning classifiers using Scikit-Learn
- Chap. 4 : Building good training datasets - Data preprocessing
- Chap. 5 : Compressing data via dimensionality reduction
- Chap. 6 : Learning best practices for model evaluation and hyperparameter tuning
- Chap. 7 : Combining different models for ensemble learning
- Chap. 8 : Applying machine learning to sentiment analysis
- Chap. 9 : Predicting continuous target variables with regression analysis
- Chap. 10 : Working with unlabeled data - Clustering analysis
- Chap. 11 : Implementing a multiplayer artificial neural network from scratch
- Chap. 12 : Parallelizing neural network training with PyTorch
- Chap. 13 : Going deeper - The mechanics of PyTorch
- Chap. 14 : Classifying images with deep convolutional neural networks
- Chap. 15 : Modeling sequential data using recurrent neural networks
- Chap. 16 : Transformers - Improving natural language processing with attention mechanisms
- Chap. 17 : Generative adversarial networks for synthesizing new data
- Chap. 18 : Graph neural networks for capturing dependencies in graph structured data
- Chap. 19 : Reinforcement learning for decision making in complex environments