Study of Various Machine Learning and Deep Learning Libraries/Platforms with Their Usage Perspective
By: Champaneria, Tushar
.
Contributor(s): Nimavat, Ketakee.
Publisher: New Delhi STM Journals 2018Edition: Vol 5 (3), Sep- Dec.Description: 1 -15p.Subject(s): Computer EngineeringOnline resources: Click Here
In:
Journal of artificial intelligence research and advances (JoAIRA)Summary: Learning is a complex multi-faceted phenomenon. While we do not understand how learning happens entirely, we understand it well enough to devise models that excel at narrow domain learning. Machine learning and deep learning enable us to create models that learn and implement that learning. There is an abundance of tools that achieve the same goals in different levels of abstraction, amount of work done and flexibility to tailor learning methods. However, they are not one-trick ponies and most of the times do not prove to be suitable for all problem scenarios involving machine learning and deep learning. Often the distinction between platforms and libraries remain as: platforms provide an abstraction of the techniques and allow easy implementation of machine learning at scale whereas libraries provide methods to build tailored solutions and often will involve coding from scratch. Depending on who is building, the amount of time and resources available, a library as well as a platform can help one get to the solution. In this paper the aim, hence, is to analyze various available tools for building the models in order to make it easier to decide which tool to use for a given scenario
| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2021-2021420 |
Learning is a complex multi-faceted phenomenon. While we do not understand how learning happens entirely, we understand it well enough to devise models that excel at narrow domain learning. Machine learning and deep learning enable us to create models that learn and implement that learning. There is an abundance of tools that achieve the same goals in different levels of abstraction, amount of work done and flexibility to tailor learning methods. However, they are not one-trick ponies and most of the times do not prove to be suitable for all problem scenarios involving machine learning and deep learning. Often the distinction between platforms and libraries remain as: platforms provide an abstraction of the techniques and allow easy implementation of machine learning at scale whereas libraries provide methods to build tailored solutions and often will involve coding from scratch. Depending on who is building, the amount of time and resources available, a library as well as a platform can help one get to the solution. In this paper the aim, hence, is to analyze various available tools for building the models in order to make it easier to decide which tool to use for a given scenario
Click on an image to view it in the image viewer
There are no comments for this item.