What is TensorFlow? How does it work – Know Everything About Google’s Open Source AI:
Hello, Readers. It’s Monday!
“Google is releasing a new TensorFlow object detection API to make it easier for developers and researchers to identify objects within images. Google is trying to offer the best of simplicity and performance” Posted on , by John Mannes @TechCrunch – [Quick Techie Update]
TensorFlow is a Google’s new artificial intelligence (AI) system. Which is now an open source i.e. any developer can use it. Google has used it for a number of applications. For example, Google search, Google’s voice recognition application, Google Translate & Google Photos – Now it’s quite good at search because it uses TensorFlow to recognize places based on popular landmarks or characteristics of that particular image.
But what is TensorFlow? Let me explain you first!
An open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. To completely understand it, you need basic knowledge of artificial intelligence (AI) and deep learning. We already explained artificial intelligence in one of our previous articles and covering deep learning in the near future.
But then it’s okay! We will try to brief you about the same in a quite simple way. Now just know How does it work?
The simplest way to understand TensorFlow and Google’s approach to Artificial Intelligence (AI) is with image recognition. In 2011, Google created DistBelief, which used machine learning to identify what’s in a photo by recognizing certain patterns and things as shown below.
This includes deep neural network used for learning to recognize a cat. The system was made using positive reinforcement, the machine was given an image and asked if the image was a cat. If the machine was correct, it was told so. But if the machine was wrong, the system was adjusted to recognize different patterns in an image so that it was more likely to get it right next time.
TensorFlow takes the concept a step further by using deep learning, or an artificial neural network composed of many layers. Basically, it sorts through layers of data, called nodes, to learn that the image it’s viewing is of a cat. The first layer will ask the system to look for something as basic as determining the general shape in the picture. The system then moves, or flows, to the next data set – like looking for paws in the photo.
The system moves from node to node to compile enough information to say that the image is, in fact, of a cat. That flow process is called a tensor, hence the name TensorFlow.
You will get More details on TensorFlow@Google’s Open Source Blog.
One Article was posted recently on Thursday, June 15, 2017 ‘Supercharge your Computer Vision models with the TensorFlow Object Detection API’ You must go through it once. Click.
That’s it for today guys! Hope you like the Article! We will surely brief the terms and the topic more just lets us know if required. Thanks for reading. Stay tuned for more updates. Do check out our amazing new categories & don’t forget to share the article and your opinions in the comment box below.
(After TensorFlow – Know Everything About Google’s Open Source AI, also read)
Article By Saurabh Sharma