What is TensorFlow?
TensorFlow is a platform-independent program library used for artificial intelligence (AI) and machine learning (ML) tasks. The software was originally developed by Google for internal use. The framework excels in a wide range of applications and enables the design of autonomous neural networks. The software offers first-class scalability and can be operated equally well on single computers up to gigantic server clusters.
What are the advantages of TensorFlow?
The use of the framework offers a variety of advantages. On the one hand, the software is characterized by its excellent performance and scalability. On the other hand, TensorFlow, in contrast to comparable tools, is able to design and train its own models.
The framework is ready for use on a variety of different platforms, such as:
- Single computers
- server clusters
- distributed and embedded systems
Probably the biggest advantage of the framework is reflected in the fact that it does not require translation of the code into other programming languages. This keeps the programming effort within limits.
On what basis is TensorFlow based ?
The so-called “graph” represents the basic element on which TensorFlow is based. A graph is an abstracted representation of a mathematical problem. The graph consists of edges and nodes that are connected to each other. The nodes are used to represent data and mathematical Operations. The connection of the individual nodes creates a complex framework that provides the mathematical scheme for the neural network.
More information on this topic can be found here:
Do you have any more questions?