AIPrimer.AI
  • 🚦AI Primer In Transportation
  • CHAPTER 1 - INTRODUCTION TO MACHINE LEARNING
    • Machine Learning in Transportation
    • What is Machine Learning?
    • Types of Machine Learning
      • Supervised Learning
      • Unsupervised Learning
      • Semi-supervised Learning
      • Reinforced Learning
    • Fundamental concepts of machine learning
      • Model Training and Testing
      • Evaluating the Model’s Prediction Accuracy
      • The Underfitting and Overfitting Problems
      • Bias-Variance Tradeoff in Overfitting
      • Model Validation Techniques
      • Hyperparameter Tuning
      • Model Regularization
      • The Curse of Ddimensionality
    • Machine Learning versus Statistics
  • CHAPTER 2 - SUPERVISED METHODS
    • Supervised Learning_Complete Draft
    • K-Nearest Neighbor (KNN) Algorithm
    • Tree-Based Methods
    • Boosting
    • Support Vector Machines (SVMs)
  • CHAPTER 3 - UNSUPERVISED LEARNING
    • Principal Component Analysis
      • How Does It Work?
      • Interpretation of PCA result
      • Applications in Transportation
    • CLUSTERING
      • K-MEANS
      • SPECTRAL CLUSTERING
      • Hierarchical Clustering
    • REFERENCE
  • CHAPTER 4 - NEURAL NETWORK
    • The Basic Paradigm: Multilayer Perceptron
    • Regression and Classification Problems with Neural Networks
    • Advanced Topologies
      • Modular Network
      • Coactive Neuro–Fuzzy Inference System
      • Recurrent Neural Networks
      • Jordan-Elman Network
      • Time-Lagged Feed-Forward Network
      • Deep Neural Networks
  • CHAPTER 5 - DEEP LEARNING
    • Convolutional Neural Networks
      • Introduction
      • Convolution Operation
      • Typical Layer Structure
      • Parameters and Hyperparameters
      • Summary of Key Features
      • Training of CNN
      • Transfer Learning
    • Recurrent Neural Networks
      • Introduction
      • Long Short-Term Memory Neural Network
      • Application in transportation
    • Recent Development
      • AlexNet, ZFNet, VggNet, and GoogLeNet
      • ResNet
      • U-Net: Full Convolutional Network
      • R-CNN, Fast R-CNN, and Faster R-CNN
      • Mask R-CNN
      • SSD and YOLO
      • RetinaNet
      • MobileNets
      • Deformable Convolution Networks
      • CenterNet
      • Exemplar Applications in Transportation
    • Reference
  • CHAPTER 6 - REINFORCEMENT LEARNING
    • Introduction
    • Reinforcement Learning Algorithms
    • Model-free v.s. Model-based Reinforcement Learning
    • Applications of Reinforcement Learning to Transportation and Traffic Engineering
    • REFERENCE
  • CHAPTER 7 - IMPLEMENTING ML AND COMPUTATIONAL REQUIREMENTS
    • Data Pipeline for Machine Learning
      • Introduction
      • Problem Definition
      • Data Ingestion
      • Data Preparation
      • Data Segregation
      • Model Training
      • Model Deployment
      • Performance Monitoring
    • Implementation Tools: The Machine Learning Ecosystem
      • Machine Learning Framework
      • Data Ingestion tools
      • Databases
      • Programming Languages
      • Visualization Tools
    • Cloud Computing
      • Types and Services
    • High-Performance Computing
      • Deployment on-premise vs on-cloud
      • Case Study: Data-driven approach for the implementation of Variable Speed Limit
      • Conclusion
  • CHAPTER 8 - RESOURCES
    • Mathematics and Statistics
    • Programming, languages, and software
    • Machine learning environments
    • Tools of the Trade
    • Online Learning Sites
    • Key Math Concepts
  • REFERENCES
  • IMPROVEMENT BACKLOG
Powered by GitBook
On this page
  1. CHAPTER 7 - IMPLEMENTING ML AND COMPUTATIONAL REQUIREMENTS
  2. Data Pipeline for Machine Learning

Model Deployment

Deploying the model could mean it's available to a small group of people within an organization or a customer operating on the other side of the planet. For each of these user groups, it is best advised to provide the machine learning model as a service that they can access for their purpose. This service can be provided in a production environment to which the user is granted complete access.

Machine Learning models can be deployed in offline or online mode. In offline mode, the model conducts batch prediction. When a request for service is made, the data is loaded dynamically into memory as a separate process, then call the prediction functions, unload it from memory and free the sources. In the case of online mode, the model can be deployed in a container to a service cluster which is distributed into many servers.

When handling big data, large computing power is the need of the hour. In that case, machine learning models (offline or online) can be deployed in either of the following ways.

  1. Cloud-Computing: Any service offered via the Internet (“cloud”) is referred to as Cloud computing. Cloud computing services include storage, database, software, networking, analytics or intelligence which can be offered via the Internet. These services can be broadly categorized as Infrastructure, Platform and Software.

  2. High-Performance Computing on-premise: High-Performance computing is the use of supercomputers for performing complex computations and parallel processing on a large scale. When deployed on-site, a network of computers (referred to as clusters) with high processing power, large memory space and strong network connections is set up. These computers collectively perform the computations with high efficiency in less processing time.

  3. High-Performance Computing on cloud: Deploying several high processing computers in a cloud base and accessing them via the internet is HPC on cloud. It combines the best of cloud computing and high-performance computing and provides for flexible scalability to grow or reduce the infrastructure based on the workload at hand.

PreviousModel TrainingNextPerformance Monitoring

Last updated 1 year ago