MLTFGOGoogleGO-MLTF1<p>This course teaches participants the following skills:</p> <ul> <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><p>To get the most out of this course, participants should have: </p> <ul> <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><ul> <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><h4>Module 1: Machine Learning on Google Cloud Platform</h4><ul> <li>Effective ML</li><li>Fully Managed ML</li></ul><h4>Module 2: Explore the Data</h4><ul> <li>Exploring the Dataset</li><li>BigQuery</li><li>BigQuery and AI Platform Notebooks</li></ul><h4>Module 3: Creating the Dataset</h4><ul> <li>Creating a Dataset</li></ul><h4>Module 4: Build the Model</h4><ul> <li>Build the Model</li></ul><h4>Module 5: Operationalize the Model</h4><ul> <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> <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> <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> <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> <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> <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> <li>Images as Visual Data</li><li>Structured vs. Unstructured Data</li></ul><h4>Module 12: Linear and DNN Models</h4><ul> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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> <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>This course teaches participants the following skills: - Implement the various flavors of production ML systems—static, dynamic, and continuous training; static and dynamic inference; and batch and online processing - 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 - 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 - Forecast time-series values using CNNs, recurrent neural networks (RNNs), and LSTMs - Apply ML to natural language text using CNNs, RNNs, LSTMs, reusable word embeddings, and encoder-decoder generative models - Implement content-based, collaborative, hybrid, and neural recommendation models in TensorFlowTo get the most out of this course, participants should have: - Knowledge of machine learning and TensorFlow to the level covered in Machine Learning on Google Cloud coursework - Experience coding in Python - Knowledge of basic statistics - Knowledge of SQL and cloud computing (helpful)- Data Engineers and programmers interested in learning how to apply machine learning in practice - Anyone interested in learning how to leverage machine learning in their enterpriseModule 1: Machine Learning on Google Cloud Platform - Effective ML - Fully Managed ML Module 2: Explore the Data - Exploring the Dataset - BigQuery - BigQuery and AI Platform Notebooks Module 3: Creating the Dataset - Creating a Dataset Module 4: Build the Model - Build the Model Module 5: Operationalize the Model - Operationalizing the Model - Cloud AI Platform - Train and Deploy with Cloud AI Platform - BigQuery ML - Deploying and Predicting with Cloud AI Platform Module 6: Architecting Production ML Systems - The Components of an ML System - The Components of an ML System: Data Analysis and Validation - The Components of an ML System: Data Transformation + Trainer - The Components of an ML System: Tuner + Model Evaluation and Validation - The Components of an ML System: Serving - The Components of an ML System: Orchestration + Workflow - The Components of an ML System: Integrated Frontend + Storage - Training Design Decisions - Serving Design Decisions - Designing from Scratch Module 7: Ingesting Data for Cloud-Based Analytics and ML - Data On-Premises - Large Datasets - Data on Other Clouds - Existing Databases Module 8: Designing Adaptable ML Systems - Adapting to Data - Changing Distributions - Right and Wrong Decisions - System Failure - Mitigating Training-Serving Skew Through Design - Debugging a Production Model Module 9: Designing High-Performance ML Systems - Training - Predictions - Why Distributed Training? - Distributed Training Architectures - Faster Input Pipelines - Native TensorFlow Operations - TensorFlow Records - Parallel Pipelines - Data Parallelism with All Reduce - Parameter Server Approach - Inference Module 10: Hybrid ML Systems - Machine Learning on Hybrid Cloud - KubeFlow - Embedded Models - TensorFlow Lite - Optimizing for Mobile Module 11: Welcome to Image Understanding with TensorFlow on GCP - Images as Visual Data - Structured vs. Unstructured Data Module 12: Linear and DNN Models - Linear Models - DNN Models Review - Review: What is Dropout? Module 13: Convolutional Neural Networks (CNNs) - Understanding Convolutions - CNN Model Parameters - Working with Pooling Layers - Implementing CNNs with TensorFlow Module 14: Dealing with Data Scarcity - The Data Scarcity Problem - Data Augmentation - Transfer Learning - No Data, No Problem Module 15: Going Deeper Faster - Batch Normalization - Residual Networks - Accelerators (CPU vs GPU, TPU) - TPU Estimator - Neural Architecture Search Module 16: Pre-built ML Models for Image Classification - Pre-Built ML Models - Cloud Vision API - AutoML Vision - AutoML Architecture Module 17: Working with Sequences - Sequence Data and Models - From Sequences to Inputs - Modeling Sequences with Linear Models - Modeling Sequences with DNNs - Modeling Sequences with CNNs - The Variable-Length problem Module 18: Recurrent Neural Networks - Introducing Recurrent Neural Networks - How RNNs Represent the Past - The Limits of What RNNs Can Represent - The Vanishing Gradient Problem Module 19: Dealing with Longer Sequences - LSTMs and GRUs - RNNs in TensorFlow - Deep RNNs - Improving our Loss Function - Working with Real Data Module 20: Text Classification - Working with Text - Text Classification - Selecting a Model - Python vs Native TensorFlow Module 21: Reusable Embeddings - Historical Methods of Making Word Embeddings - Modern Methods of Making Word Embeddings - Introducing TensorFlow Hub - Using TensorFlow Hub Within an Estimator Module 22: Recurrent Neural NetworksEncoder-Decoder Models - Introducing Encoder-Decoder Networks - Attention Networks - Training Encoder-Decoder Models with TensorFlow - Introducing Tensor2Tensor - AutoML Translation - Dialogflow Module 23: Recommendation Systems Overview - Types of Recommendation Systems - Content-Based or Collaborative - Recommendation System Pitfalls Module 24: Content-Based Recommendation Systems - Content-Based Recommendation Systems - Similarity Measures - Building a User Vector - Making Recommendations Using a User Vector - Making Recommendations for Many Users - Using Neural Networks for Content-Based Recommendation Systems Module 25: Collaborative Filtering Recommendation Systems - Types of User Feedback Data - Embedding Users and Items - Factorization Approaches - The ALS Algorithm - Preparing Input Data for ALS - Creating Sparse Tensors For Efficient WALS Input - Instantiating a WALS Estimator: From Input to Estimator - Instantiating a WAL Estimator: Decoding TFRecords - Instantiating a WALS Estimator: Recovering Keys - Instantiating a WALS Estimator: Training and Prediction - Issues with Collaborative Filtering - Cold Starts Module 26: Neural Networks for Recommendation Systems - Hybrid Recommendation System - Context-Aware Recommendation Systems - Context-Aware Algorithms - Contextual Postfiltering - Modeling Using Context-Aware Algorithms Module 27: Building an End-to-End Recommendation System - Architecture Overview - Cloud Composer Overview - Cloud Composer: DAGs - Cloud Composer: Operators for ML9 - Cloud Composer: Scheduling - Cloud Composer: Triggering Workflows with Cloud Functions - Cloud Composer: Monitoring and Logging5 days1495.003250.002995.003250.0011270.002995.002995.003250.003300.003770.003250.00