TensorFlow: One of the Most Popular Framework of Machine Learning

Jul 3, 2018 | 2988 Views

Deep Learning is a subset of Machine Learning and it works on the structure and functions of a human brain. It learns from the data that is structured and uses complex algorithms to train a neural net. This is a learning mechanism. Deep learning is a neural network somewhat looks like this there is something known as an input layer and then there is an output layer and in between there are a bunch of hidden layers so typically it would be at least one hidden layer and anything more than one hidden layer is known as a deep neural network so any neural network with more than three layers altogether right based known as a deep neural.

Why TensorFlow?
TensorFlow offers API to write your code in Python, C++ and so on other languages Java as well it has integration with R as well apparently good and it supports CPUs as well as GPIOs now deep learning applications are very compute intensive especially the training process needs a lot of computation as data size is large and there are so many hydrater processors there are so much of mathematical calculations matrix multiplication and so on so forth so for that if you perform these activities on a normal CPU typically it would take much longer but GPUs are graphical processing units. All have heard GPUs in the context of games and so on because where you need the screen it needs high resolution and so on so GPUs there as the name such as graphical processing units were originally designed for that but since they are very good at handling this kind of iterative calculations and so on now they are kind of being used or leveraged rather for doing or developing deep learning applications and tensorflow supports GPUs as well as CPUs so this is the one of the major advantages of the TensorFlow.

What is Tensorflow?
It is an open source library developed by Google and open source primarily for deep learning development but tensorflow also supports traditional machine learning by the way so if you want to do some traditional machine learning we can do it however it is probably a bit of overhead we use tensor flow for doing creation and machine learning and this is really good for performing deep learning activities.

TensorFlow is an open source software library for high performance numerical computation. Its flexible architecture allows easy deployment of computation across a variety of platforms (CPUs, GPUs, TPUs), and from desktops to clusters of servers to mobile and edge devices. Originally developed by researchers and engineers from the Google Brain team within Google's AI organization, it comes with strong support for machine learning and deep learning and the flexible numerical computation core is used across many other scientific domains.

What are Tensors?
Tensors are like a multi-dimensional array in which the data is stored now when we are doing deep-learning especially the training process you will have the large amounts of data and the data is typically in a very complicated format and it really helps when you are able to put this to store. So tensors actually offer a very nice and compact way of storing the data or handling the data during computation this is not really for storing on your hard disk or things like that but in memory when you are doing the computation. 

Tensors are really very handy in terms of keeping the data compact because they are like multi-dimensional arrays so the data is stored in tensors and then it is fed into the neural network. 
Hence, tensorflow is one of the most popular machine learning frameworks. 

Source: HOB