Skip to main content

Why Tensorflow


You have a lot of data which you want to make sense of, learn patterns, but you don't have the necessary expertice to develop algorithms that will learn through the data. Ofcourse you can develop your own machine learning algorithms to make sense of the data. There might be benifits in developing your own algorithms, proprietary being one, but you might have to invest time and money.

What if you have access to ready made machine learning algorithms which you just have to use in your products? Google's Tensorflow offers such tried and tested algorithms using APIs that you just have to call in your programs. All you have to provide is data, and Tensorflow will take care of the intelligence to learn.

Tensorflow adds the following capabilities to your products
1. Access to machine learning algorithms such as Neural Networks.
2. Increase performance of your models using multiple CPUs and GPUs without change in code.
3. Do numerical computations using data flow graphs.

To learn more about Tensorflow check Tensorflows official website at

Check the white paper of Tensorflow at

Check the presentation of Jeff Dean to know more about Tensorflow applications at Google http://static.googleusercontent.com/media/research.google.com/en//people/jeff/BayLearn2015.pdf

Install Tensorflow using

Go through Tensorflow tutorials at

Download and check source code of tutorials at


Keep following this blog as the researchers at Cerelabs try their hands on Tensorflow...

Comments

Popular posts from this blog

Implement XOR in Tensorflow

XOR is considered as the 'Hello World' of Neural Networks. It seems like the best problem to try your first TensorFlow program.

Tensorflow makes it easy to build a neural network with few tweaks. All you have to do is make a graph and you have a neural network that learns the XOR function.

Why XOR? Well, XOR is the reason why backpropogation was invented in the first place. A single layer perceptron although quite successful in learning the AND and OR functions, can't learn XOR (Table 1) as it is just a linear classifier, and XOR is a linearly inseparable pattern (Figure 1). Thus the single layer perceptron goes into a panic mode while learning XOR – it can't just do that. 

Deep Propogation algorithm comes for the rescue. It learns an XOR by adding two lines L1 and L2 (Figure 2). This post assumes you know how the backpropogation algorithm works.



Following are the steps to implement the neural network in Figure 3 for XOR in Tensorflow:
1. Import necessary libraries
impo…

Understanding Generative Adversarial Networks - Part II

In "Understanding Generative Adversarial Networks - Part I" you gained a conceptual understanding of how GAN works. In this post let us get a mathematical understanding of GANs.
The loss functions can be designed most easily using the idea of zero-sum games. 
The sum of the costs of all players is 0. This is the Minimax algorithm for GANs
Let’s break it down.
Some terminology: V(D, G) : The value function for a minimax game E(X) : Expectation of a random variable X, also equal to its average value D(x) : The discriminator output for an input x from real data, represents probability G(z): The generator's output when its given z from the noise distribution D(G(z)): Combining the above, this represents the output of the discriminator when 
given a generated image G(z) as input
Now, as explained above, the discriminator is the maximizer and hence it tries to 
maximize