AI Workflow: Enterprise Model Deployment

Start Date: 01/24/2021

Course Type: Common Course

Course Link:

About Course

This is the fifth course in the IBM AI Enterprise Workflow Certification specialization.   You are STRONGLY encouraged to complete these courses in order as they are not individual independent courses, but part of a workflow where each course builds on the previous ones. This course introduces you to an area that few data scientists are able to experience: Deploying models for use in large enterprises.  Apache Spark is a very commonly used framework for running machine learning models.  Best practices for using Spark will be covered in this course.  Best practices for data manipulation, model training, and model tuning will also be covered.  The use case will call for the creation and deployment of a recommender system. The course wraps up with an introduction to model deployment technologies.   By the end of this course you will be able to: 1.  Use Apache Spark's RDDs, dataframes, and a pipeline 2.  Employ spark-submit scripts to interface with Spark environments 3.  Explain how collaborative filtering and content-based filtering work 4.  Build a data ingestion pipeline using Apache Spark and Apache Spark streaming 5.  Analyze hyperparameters in machine learning models on Apache Spark 6.  Deploy machine learning algorithms using the Apache Spark machine learning interface 7.  Deploy a machine learning model from Watson Studio to Watson Machine Learning Who should take this course? This course targets existing data science practitioners that have expertise building machine learning models, who want to deepen their skills on building and deploying AI in large enterprises. If you are an aspiring Data Scientist, this course is NOT for you as you need real world expertise to benefit from the content of these courses. What skills should you have? It is assumed that you have completed Courses 1 through 4 of the IBM AI Enterprise Workflow specialization and you have a solid understanding of the following topics prior to starting this course: Fundamental understanding of Linear Algebra; Understand sampling, probability theory, and probability distributions; Knowledge of descriptive and inferential statistical concepts; General understanding of machine learning techniques and best practices; Practiced understanding of Python and the packages commonly used in data science: NumPy, Pandas, matplotlib, scikit-learn; Familiarity with IBM Watson Studio; Familiarity with the design thinking process.

Coursera Plus banner featuring three learners and university partner logos

Course Introduction

AI Workflow: Enterprise Model Deployment This course will provide an introduction to the advanced AI concepts, methods and techniques required to design and control autonomous aerial vehicles (or drones), or A/V's, for specific applications. The course will also cover the design considerations for a drone- or A/V-based telepresence that you would need to consider, including the sensors and algorithms that would be used to detect and track you, the cost of such a system and the size and weight of the payload, the performance of such system and the interaction between these two, and other factors. The course will discuss some of the most prominent and important areas of AI, including machine learning, neural networks, deep learning and deep learning for A/V's. The course should also give you a sense of what an enterprise-level drone- or A/V-based telepresence is all about, from planning and scheduling, to cost, to the various subsystems and services that would be required, to the design considerations for such systems and services. This is the third and final course in the specialization about AI for Workforce Development and Artificial Intelligence (known colloquially as "AI for B2B," or Business to Business). If you are interested in becoming a drone/A/V telepresence advisor, please take a look at the specialization topics in this course. This course will challenge you to think more deeply than in terms of specific

Course Tag

Related Wiki Topic

Article Example
Workflow Reference Model First published in 1995 the Workflow Reference Model was developed by the Workflow Management Coalition to define a workflow management system and to identify the most important system interfaces. Other WfMC standards make reference to this model.
Collaborative workflow To be effective, the enterprise collaborative workflow solution should include:
NIST Enterprise Architecture Model NIST Enterprise Architecture Model (NIST EA Model) is a late-1980s reference model for enterprise architecture. It defines an enterprise architecture by the interrelationship between an enterprise's business, information, and technology environments.
Deployment descriptor In the Java Platform, Enterprise Edition, a deployment descriptor describes how a component, module or application (such as a web application or enterprise application) should be deployed. It directs a deployment tool to deploy a module or application with specific container options, security settings and describes specific configuration requirements. XML is used for the syntax of these deployment descriptor files.
Workflow The concept of workflow is closely related to several fields in operations research and other areas that study the nature of work, either quantitatively or qualitatively, such as artificial intelligence (in particular, the sub-discipline of AI planning) and ethnography. The term "workflow" is more commonly used in particular industries, such as printing and professional domains, where it may have particular specialized meanings.
Collaborative workflow Workflow applications brought to the modern enterprise what Henry Ford's assembly line brought to manufacturing: improved efficiency, uniform outcomes, and greater throughput.
Content-oriented workflow models Most content-oriented workflow approaches provide a life-cycle model for content units, such that workflow progression can be qualified by conditions on the state of the units.
Imixs-Workflow The project is based on the Java Enterprise Architecture (JEE) and represents a scalable and transactional framework for workflow management solutions. A major goal of the technology is to simplify the software build process in modern business applications. The project takes advantage of the JEE component model, and allows to reuse all components without limiting the capabilities of the Java EE architecture.
Kepler scientific workflow system Kepler provides a model for the semantic annotation of workflow components using terms drawn from an ontology. These annotations support many advanced features, including improved search capabilities, automated workflow validation, and improved workflow editing.
Content-oriented workflow models Case handling is orthogonal to content-oriented workflows. Some content-oriented workflow approaches are not related to case handling, but, for example, to automated manufacturing. In contrast, systems that are considered to be case handling systems (CHS) but which do not apply a content-oriented workflow model are, for example, BPMone (formerly PROTOS and FLOWer) from Pallas Athena, ECHO from Digital, CMDT from ICL, and Vectus from London Bridge Group. In conclusion, those content-oriented workflow approaches that are tightly related to case handling are the #Resource-driven workflow model and the #Distributed Document-oriented workflow model.
Content-oriented workflow models The workflow model reflects the paper-based working practice in inter-institutional healthcare scenarios.
Kepler scientific workflow system Kepler differs from many of the other bioinformatics workflow management systems in that it separates the structure of the workflow model from its model of computation, such that different models for the computation of the workflow can be bound to a given workflow graph. Kepler inherits several common models of computation from the Ptolemy system, including Synchronous Data Flow (SDF), Continuous Time (CT), Process Network (PN), and Dynamic Data Flow (DDF), among others.
NIST Enterprise Architecture Model To support the NIST Enterprise Architecture Model in the 1990s, it was widely promoted within the U.S. federal government as Enterprise Architecture management tool. The NIST Enterprise Architecture Model is applied as foundation in multiple Enterprise Architecture frameworks of U.S. Federal government agencies and in the overall Federal Enterprise Architecture Framework. In coordinating this effort the NIST model was further explained and extended in the 1997 "Memoranda 97-16 (Information Technology Architectures)" issued by the US Office of Management and Budget., see further Information Technology Architecture.
Workflow A workflow management system (WfMS) is a software system for the set-up, performance and monitoring of a defined sequence of tasks, arranged as a workflow.
NIST Enterprise Architecture Model The NIST Enterprise Architecture Model is a five-layered model for enterprise architecture, designed for organizing, planning, and building an integrated set of information and information technology architectures. The five layers are defined separately but are interrelated and interwoven. The model defined the interrelation as follows:
Imixs-Workflow Imixs-Workflow provides the results of the project under the GPL with a dual-license model, to meet the usage and distribution requirements of different types of users.
Content-oriented workflow models The distribution of the enterprise application landscape with its business services is considered, yet, the workflow engine itself seems to be centralized.
Deployment descriptor In Java EE, there are two types of deployment descriptors: "Java EE deployment descriptors" and "runtime deployment descriptors". The Java EE deployment descriptors are defined by the language specification, whereas the runtime descriptors are defined by the vendor of each container implementation. For example, the "web.xml" file is a standard Java EE deployment descriptor, specified in the Java Servlet specification, but the "sun-web.xml" file contains configuration data specific to the Sun GlassFish Enterprise Server implementation.
Content-oriented workflow models The data-driven process structures provides a sophisticated workflow model being specialized on hierarchical write-and-review-processes.
Enterprise control An enterprise control system is the open architecture framework to integrate control systems with the enterprise while adding functions to improve business performance including MES, optimization, workflow, quality management, and asset management.