{"course":{"productid":20024,"modality":1,"active":true,"language":"en","title":"Advanced Machine Learning with TensorFlow on Google Cloud Platform","productcode":"MLTF","vendorcode":"GO","vendorname":"Google","fullproductcode":"GO-MLTF","courseware":{"has_ekit":false,"has_printkit":true,"language":"en"},"url":"https:\/\/portal.flane.ch\/course\/google-mltf","objective":"<p>This course teaches participants the following skills:<\/p>\n<ul>\n<li>Implement the various flavors of production ML systems&mdash;static, dynamic, and continuous training; static and dynamic inference; and batch and online processing<\/li><li>Solve an ML problem by building an end-to-end pipeline, going from data exploration, preprocessing, feature engineering, model building, hyperparameter tuning, deployment, and serving<\/li><li>Develop a range of image classification models from simple linear models to high-performing convolutional neural networks (CNNs) with batch normalization, augmentation, and transfer learning<\/li><li>Forecast time-series values using CNNs, recurrent neural networks (RNNs), and LSTMs<\/li><li>Apply ML to natural language text using CNNs, RNNs, LSTMs, reusable word embeddings, and encoder-decoder generative models<\/li><li>Implement content-based, collaborative, hybrid, and neural recommendation models in TensorFlow<\/li><\/ul>","essentials":"<p>To get the most out of this course, participants should have:\n<\/p>\n<ul>\n<li>Knowledge of machine learning and TensorFlow to the level covered in Machine Learning on Google Cloud coursework<\/li><li>Experience coding in Python<\/li><li>Knowledge of basic statistics<\/li><li>Knowledge of SQL and cloud computing (helpful)<\/li><\/ul>","audience":"<ul>\n<li>Data Engineers and programmers interested in learning how to apply machine learning in practice<\/li><li>Anyone interested in learning how to leverage machine learning in their enterprise<\/li><\/ul>","outline":"<h4>Module 1: Machine Learning on Google Cloud Platform<\/h4><ul>\n<li>Effective ML<\/li><li>Fully Managed ML<\/li><\/ul><h4>Module 2: Explore the Data<\/h4><ul>\n<li>Exploring the Dataset<\/li><li>BigQuery<\/li><li>BigQuery and AI Platform Notebooks<\/li><\/ul><h4>Module 3: Creating the Dataset<\/h4><ul>\n<li>Creating a Dataset<\/li><\/ul><h4>Module 4: Build the Model<\/h4><ul>\n<li>Build the Model<\/li><\/ul><h4>Module 5: Operationalize the Model<\/h4><ul>\n<li>Operationalizing the Model<\/li><li>Cloud AI Platform<\/li><li>Train and Deploy with Cloud AI Platform<\/li><li>BigQuery ML<\/li><li>Deploying and Predicting with Cloud AI Platform<\/li><\/ul><h4>Module 6: Architecting Production ML Systems<\/h4><ul>\n<li>The Components of an ML System<\/li><li>The Components of an ML System: Data Analysis and Validation<\/li><li>The Components of an ML System: Data Transformation + Trainer<\/li><li>The Components of an ML System: Tuner + Model Evaluation and Validation<\/li><li>The Components of an ML System: Serving<\/li><li>The Components of an ML System: Orchestration + Workflow<\/li><li>The Components of an ML System: Integrated Frontend + Storage<\/li><li>Training Design Decisions<\/li><li>Serving Design Decisions<\/li><li>Designing from Scratch<\/li><\/ul><h4>Module 7: Ingesting Data for Cloud-Based Analytics and ML<\/h4><ul>\n<li>Data On-Premises<\/li><li>Large Datasets<\/li><li>Data on Other Clouds<\/li><li>Existing Databases<\/li><\/ul><h4>Module 8: Designing Adaptable ML Systems<\/h4><ul>\n<li>Adapting to Data<\/li><li>Changing Distributions<\/li><li>Right and Wrong Decisions<\/li><li>System Failure<\/li><li>Mitigating Training-Serving Skew Through Design<\/li><li>Debugging a Production Model<\/li><\/ul><h4>Module 9: Designing High-Performance ML Systems<\/h4><ul>\n<li>Training<\/li><li>Predictions<\/li><li>Why Distributed Training?<\/li><li>Distributed Training Architectures<\/li><li>Faster Input Pipelines<\/li><li>Native TensorFlow Operations<\/li><li>TensorFlow Records<\/li><li>Parallel Pipelines<\/li><li>Data Parallelism with All Reduce<\/li><li>Parameter Server Approach<\/li><li>Inference<\/li><\/ul><h4>Module 10: Hybrid ML Systems<\/h4><ul>\n<li>Machine Learning on Hybrid Cloud<\/li><li>KubeFlow<\/li><li>Embedded Models<\/li><li>TensorFlow Lite<\/li><li>Optimizing for Mobile<\/li><\/ul><h4>Module 11: Welcome to Image Understanding with TensorFlow on GCP<\/h4><ul>\n<li>Images as Visual Data<\/li><li>Structured vs. Unstructured Data<\/li><\/ul><h4>Module 12: Linear and DNN Models<\/h4><ul>\n<li>Linear Models<\/li><li>DNN Models Review<\/li><li>Review: What is Dropout?<\/li><\/ul><h4>Module 13: Convolutional Neural Networks (CNNs)<\/h4><ul>\n<li>Understanding Convolutions<\/li><li>CNN Model Parameters<\/li><li>Working with Pooling Layers<\/li><li>Implementing CNNs with TensorFlow<\/li><\/ul><h4>Module 14: Dealing with Data Scarcity<\/h4><ul>\n<li>The Data Scarcity Problem<\/li><li>Data Augmentation<\/li><li>Transfer Learning<\/li><li>No Data, No Problem<\/li><\/ul><h4>Module 15: Going Deeper Faster<\/h4><ul>\n<li>Batch Normalization<\/li><li>Residual Networks<\/li><li>Accelerators (CPU vs GPU, TPU)<\/li><li>TPU Estimator<\/li><li>Neural Architecture Search<\/li><\/ul><h4>Module 16: Pre-built ML Models for Image Classification<\/h4><ul>\n<li>Pre-Built ML Models<\/li><li>Cloud Vision API<\/li><li>AutoML Vision<\/li><li>AutoML Architecture<\/li><\/ul><h4>Module 17: Working with Sequences<\/h4><ul>\n<li>Sequence Data and Models<\/li><li>From Sequences to Inputs<\/li><li>Modeling Sequences with Linear Models<\/li><li>Modeling Sequences with DNNs<\/li><li>Modeling Sequences with CNNs<\/li><li>The Variable-Length problem<\/li><\/ul><h4>Module 18: Recurrent Neural Networks<\/h4><ul>\n<li>Introducing Recurrent Neural Networks<\/li><li>How RNNs Represent the Past<\/li><li>The Limits of What RNNs Can Represent<\/li><li>The Vanishing Gradient Problem<\/li><\/ul><h4>Module 19: Dealing with Longer Sequences<\/h4><ul>\n<li>LSTMs and GRUs<\/li><li>RNNs in TensorFlow<\/li><li>Deep RNNs<\/li><li>Improving our Loss Function<\/li><li>Working with Real Data<\/li><\/ul><h4>Module 20: Text Classification<\/h4><ul>\n<li>Working with Text<\/li><li>Text Classification<\/li><li>Selecting a Model<\/li><li>Python vs Native TensorFlow<\/li><\/ul><h4>Module 21: Reusable Embeddings<\/h4><ul>\n<li>Historical Methods of Making Word Embeddings<\/li><li>Modern Methods of Making Word Embeddings<\/li><li>Introducing TensorFlow Hub<\/li><li>Using TensorFlow Hub Within an Estimator<\/li><\/ul><h4>Module 22: Recurrent Neural NetworksEncoder-Decoder Models<\/h4><ul>\n<li>Introducing Encoder-Decoder Networks<\/li><li>Attention Networks<\/li><li>Training Encoder-Decoder Models with TensorFlow<\/li><li>Introducing Tensor2Tensor<\/li><li>AutoML Translation<\/li><li>Dialogflow<\/li><\/ul><h4>Module 23: Recommendation Systems Overview<\/h4><ul>\n<li>Types of Recommendation Systems<\/li><li>Content-Based or Collaborative<\/li><li>Recommendation System Pitfalls<\/li><\/ul><h4>Module 24: Content-Based Recommendation Systems<\/h4><ul>\n<li>Content-Based Recommendation Systems<\/li><li>Similarity Measures<\/li><li>Building a User Vector<\/li><li>Making Recommendations Using a User Vector<\/li><li>Making Recommendations for Many Users<\/li><li>Using Neural Networks for Content-Based Recommendation Systems<\/li><\/ul><h4>Module 25: Collaborative Filtering Recommendation Systems<\/h4><ul>\n<li>Types of User Feedback Data<\/li><li>Embedding Users and Items<\/li><li>Factorization Approaches<\/li><li>The ALS Algorithm<\/li><li>Preparing Input Data for ALS<\/li><li>Creating Sparse Tensors For Efficient WALS Input<\/li><li>Instantiating a WALS Estimator: From Input to Estimator<\/li><li>Instantiating a WAL Estimator: Decoding TFRecords<\/li><li>Instantiating a WALS Estimator: Recovering Keys<\/li><li>Instantiating a WALS Estimator: Training and Prediction<\/li><li>Issues with Collaborative Filtering<\/li><li>Cold Starts<\/li><\/ul><h4>Module 26: Neural Networks for Recommendation Systems<\/h4><ul>\n<li>Hybrid Recommendation System<\/li><li>Context-Aware Recommendation Systems<\/li><li>Context-Aware Algorithms<\/li><li>Contextual Postfiltering<\/li><li>Modeling Using Context-Aware Algorithms<\/li><\/ul><h4>Module 27: Building an End-to-End Recommendation System<\/h4><ul>\n<li>Architecture Overview<\/li><li>Cloud Composer Overview<\/li><li>Cloud Composer: DAGs<\/li><li>Cloud Composer: Operators for ML9<\/li><li>Cloud Composer: Scheduling<\/li><li>Cloud Composer: Triggering Workflows with Cloud Functions<\/li><li>Cloud Composer: Monitoring and Logging<\/li><\/ul>","summary":"<p>This course will give you hands-on experience optimizing, deploying, and scaling a variety of production ML models. You&rsquo;ll learn how to build scalable, accurate, and production-ready models for structured data, image data, time-series, and natural language text, along with recommendation systems.<\/p>","objective_plain":"This course teaches participants the following skills:\n\n\n- Implement the various flavors of production ML systems\u2014static, dynamic, and continuous training; static and dynamic inference; and batch and online processing\n- Solve an ML problem by building an end-to-end pipeline, going from data exploration, preprocessing, feature engineering, model building, hyperparameter tuning, deployment, and serving\n- Develop a range of image classification models from simple linear models to high-performing convolutional neural networks (CNNs) with batch normalization, augmentation, and transfer learning\n- Forecast time-series values using CNNs, recurrent neural networks (RNNs), and LSTMs\n- Apply ML to natural language text using CNNs, RNNs, LSTMs, reusable word embeddings, and encoder-decoder generative models\n- Implement content-based, collaborative, hybrid, and neural recommendation models in TensorFlow","essentials_plain":"To get the most out of this course, participants should have:\n\n\n\n- Knowledge of machine learning and TensorFlow to the level covered in Machine Learning on Google Cloud coursework\n- Experience coding in Python\n- Knowledge of basic statistics\n- Knowledge of SQL and cloud computing (helpful)","audience_plain":"- Data Engineers and programmers interested in learning how to apply machine learning in practice\n- Anyone interested in learning how to leverage machine learning in their enterprise","outline_plain":"Module 1: Machine Learning on Google Cloud Platform\n\n\n- Effective ML\n- Fully Managed ML\nModule 2: Explore the Data\n\n\n- Exploring the Dataset\n- BigQuery\n- BigQuery and AI Platform Notebooks\nModule 3: Creating the Dataset\n\n\n- Creating a Dataset\nModule 4: Build the Model\n\n\n- Build the Model\nModule 5: Operationalize the Model\n\n\n- Operationalizing the Model\n- Cloud AI Platform\n- Train and Deploy with Cloud AI Platform\n- BigQuery ML\n- Deploying and Predicting with Cloud AI Platform\nModule 6: Architecting Production ML Systems\n\n\n- The Components of an ML System\n- The Components of an ML System: Data Analysis and Validation\n- The Components of an ML System: Data Transformation + Trainer\n- The Components of an ML System: Tuner + Model Evaluation and Validation\n- The Components of an ML System: Serving\n- The Components of an ML System: Orchestration + Workflow\n- The Components of an ML System: Integrated Frontend + Storage\n- Training Design Decisions\n- Serving Design Decisions\n- Designing from Scratch\nModule 7: Ingesting Data for Cloud-Based Analytics and ML\n\n\n- Data On-Premises\n- Large Datasets\n- Data on Other Clouds\n- Existing Databases\nModule 8: Designing Adaptable ML Systems\n\n\n- Adapting to Data\n- Changing Distributions\n- Right and Wrong Decisions\n- System Failure\n- Mitigating Training-Serving Skew Through Design\n- Debugging a Production Model\nModule 9: Designing High-Performance ML Systems\n\n\n- Training\n- Predictions\n- Why Distributed Training?\n- Distributed Training Architectures\n- Faster Input Pipelines\n- Native TensorFlow Operations\n- TensorFlow Records\n- Parallel Pipelines\n- Data Parallelism with All Reduce\n- Parameter Server Approach\n- Inference\nModule 10: Hybrid ML Systems\n\n\n- Machine Learning on Hybrid Cloud\n- KubeFlow\n- Embedded Models\n- TensorFlow Lite\n- Optimizing for Mobile\nModule 11: Welcome to Image Understanding with TensorFlow on GCP\n\n\n- Images as Visual Data\n- Structured vs. Unstructured Data\nModule 12: Linear and DNN Models\n\n\n- Linear Models\n- DNN Models Review\n- Review: What is Dropout?\nModule 13: Convolutional Neural Networks (CNNs)\n\n\n- Understanding Convolutions\n- CNN Model Parameters\n- Working with Pooling Layers\n- Implementing CNNs with TensorFlow\nModule 14: Dealing with Data Scarcity\n\n\n- The Data Scarcity Problem\n- Data Augmentation\n- Transfer Learning\n- No Data, No Problem\nModule 15: Going Deeper Faster\n\n\n- Batch Normalization\n- Residual Networks\n- Accelerators (CPU vs GPU, TPU)\n- TPU Estimator\n- Neural Architecture Search\nModule 16: Pre-built ML Models for Image Classification\n\n\n- Pre-Built ML Models\n- Cloud Vision API\n- AutoML Vision\n- AutoML Architecture\nModule 17: Working with Sequences\n\n\n- Sequence Data and Models\n- From Sequences to Inputs\n- Modeling Sequences with Linear Models\n- Modeling Sequences with DNNs\n- Modeling Sequences with CNNs\n- The Variable-Length problem\nModule 18: Recurrent Neural Networks\n\n\n- Introducing Recurrent Neural Networks\n- How RNNs Represent the Past\n- The Limits of What RNNs Can Represent\n- The Vanishing Gradient Problem\nModule 19: Dealing with Longer Sequences\n\n\n- LSTMs and GRUs\n- RNNs in TensorFlow\n- Deep RNNs\n- Improving our Loss Function\n- Working with Real Data\nModule 20: Text Classification\n\n\n- Working with Text\n- Text Classification\n- Selecting a Model\n- Python vs Native TensorFlow\nModule 21: Reusable Embeddings\n\n\n- Historical Methods of Making Word Embeddings\n- Modern Methods of Making Word Embeddings\n- Introducing TensorFlow Hub\n- Using TensorFlow Hub Within an Estimator\nModule 22: Recurrent Neural NetworksEncoder-Decoder Models\n\n\n- Introducing Encoder-Decoder Networks\n- Attention Networks\n- Training Encoder-Decoder Models with TensorFlow\n- Introducing Tensor2Tensor\n- AutoML Translation\n- Dialogflow\nModule 23: Recommendation Systems Overview\n\n\n- Types of Recommendation Systems\n- Content-Based or Collaborative\n- Recommendation System Pitfalls\nModule 24: Content-Based Recommendation Systems\n\n\n- Content-Based Recommendation Systems\n- Similarity Measures\n- Building a User Vector\n- Making Recommendations Using a User Vector\n- Making Recommendations for Many Users\n- Using Neural Networks for Content-Based Recommendation Systems\nModule 25: Collaborative Filtering Recommendation Systems\n\n\n- Types of User Feedback Data\n- Embedding Users and Items\n- Factorization Approaches\n- The ALS Algorithm\n- Preparing Input Data for ALS\n- Creating Sparse Tensors For Efficient WALS Input\n- Instantiating a WALS Estimator: From Input to Estimator\n- Instantiating a WAL Estimator: Decoding TFRecords\n- Instantiating a WALS Estimator: Recovering Keys\n- Instantiating a WALS Estimator: Training and Prediction\n- Issues with Collaborative Filtering\n- Cold Starts\nModule 26: Neural Networks for Recommendation Systems\n\n\n- Hybrid Recommendation System\n- Context-Aware Recommendation Systems\n- Context-Aware Algorithms\n- Contextual Postfiltering\n- Modeling Using Context-Aware Algorithms\nModule 27: Building an End-to-End Recommendation System\n\n\n- Architecture Overview\n- Cloud Composer Overview\n- Cloud Composer: DAGs\n- Cloud Composer: Operators for ML9\n- Cloud Composer: Scheduling\n- Cloud Composer: Triggering Workflows with Cloud Functions\n- Cloud Composer: Monitoring and Logging","summary_plain":"This course will give you hands-on experience optimizing, deploying, and scaling a variety of production ML models. You\u2019ll learn how to build scalable, accurate, and production-ready models for structured data, image data, time-series, and natural language text, along with recommendation systems.","skill_level":"Intermediate","version":"1","duration":{"unit":"d","value":5,"formatted":"5 days"},"pricelist":{"List Price":{"IN":{"country":"IN","currency":"USD","taxrate":12.36,"price":1495},"AT":{"country":"AT","currency":"EUR","taxrate":20,"price":3250},"SG":{"country":"SG","currency":"USD","taxrate":8,"price":2995},"DE":{"country":"DE","currency":"EUR","taxrate":19,"price":3250},"IL":{"country":"IL","currency":"ILS","taxrate":17,"price":11270},"NL":{"country":"NL","currency":"EUR","taxrate":21,"price":2995},"BE":{"country":"BE","currency":"EUR","taxrate":21,"price":2995},"SI":{"country":"SI","currency":"EUR","taxrate":20,"price":3250},"GB":{"country":"GB","currency":"GBP","taxrate":20,"price":3300},"FR":{"country":"FR","currency":"EUR","taxrate":19.6,"price":3770},"CH":{"country":"CH","currency":"CHF","taxrate":8.1,"price":3250}}},"lastchanged":"2025-09-30T15:07:53+02:00","parenturl":"https:\/\/portal.flane.ch\/swisscom\/en\/json-courses","nexturl_course_schedule":"https:\/\/portal.flane.ch\/swisscom\/en\/json-course-schedule\/20024","source_lang":"en","source":"https:\/\/portal.flane.ch\/swisscom\/en\/json-course\/google-mltf"}}