FP_Deep Learning Tools and Applications.docx - Deep...

This preview shows page 1 - 3 out of 35 pages.

Deep Learning - Tools and ApplicationsIntroduction:A Warm Welcome!Welcome to the new course onDeep Learning - Tools and Applications. In thefirst course,Deep Learning - Chorale Prelude, hope you had an introduction to thevarious neural network architectures, how each architecture fits in for a specificdatatype.In this course, you will understand the various tools that are used to implement thearchitectures and the real-world applications.Course - IntroductionYou will experience the following topics during this journey into this course.Platforms available for deep learningPopular libraries to build a deep netVarious configuration parameters to tune our deep netTechniques to improve the performance and various metrics available to measure the performanceApplications of deep netWhat is a Deep Net Platform?Adeep net platformis service that allows you to incorporate deep net in ourapplications without building one from scratch.This platform provides a set of toolsand interface to build your own custom deep net.Types of Deep Net PlatformsDeep net platforms are of two types.Software platform: This platform is available as downloadable packages that needto be deployed on your hardware.Full platform: It is available as online interactive UI to build and deploy modelswithout any coding experience.More on Deep Net Platform
Watch the video below that explains what exactly is a deep net platform.This is an auto-generated transcriptAt this point, you’re probably eager to use a deep net in one of your own applications. If that’sthe case, let me introduce you to a few platforms that allow you to utilize these nets without thehassle of building one yourself. Deep Learning platforms come in two different forms – softwareplatforms and full platforms. Let’s see how they work. A platform is a set of tools that otherpeople can build on top of. For example, think of the applications that can be built off of the toolsprovided by iOS and Android, Windows and MacOS, IBM Websphere, and even Oracle BEA. Soa Deep Learning platform provides a set of tools and an interface for building custom deep nets.Typically, they provide a user with a selection of deep nets to choose from, along with the abilityto integrate data from different sources, manipulate data, and manage models through a UI.Some platforms also help with performance if a net needs to be trained with a large data set.Have you ever used a Deep Learning platform in one of your own projects? Please commentand share your experiences. Later in the series, we will introduce you to software libraries thatwill help you code your own deep nets. There are some advantages and disadvantages of usinga platform vs. using a software library. A platform is an out-of-the-box application that lets youconfigure a deep net’s hyper-parameters through an intuitive UI; with a platform, you don’t needto know anything about coding in order to use the tools. The downside is that you areconstrained by the platform’s selection of deep nets as well as the configuration options. But foranyone looking to quickly deploy a deep net, a platform is the best way to go. A software libraryis a set of functions and modules that you can call through your own code in order to performcertain tasks. Deep net libraries give you a lot of extra flexibility with net selection and hyper-

Upload your study docs or become a

Course Hero member to access this document

Upload your study docs or become a

Course Hero member to access this document

End of preview. Want to read all 35 pages?

Upload your study docs or become a

Course Hero member to access this document

Term
Fall
Professor
NoProfessor
Tags
Machine Learning, Deep Learning Library

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture