Unravelling the mysteries of Artificial Intelligence

“Artificial Intelligence (AI) is like a child, who needs time to learn and adapt, whereas a typical IT system is like Buddha who knows everything about the problem it was supposed to solve.”              - Devesh Rajadhyax, Founder, Cere Labs. Images: By Purshi - Own work, CC BY-SA 3.0, https://commons.wikimedia.org/w/index.php?curid=9827197 By Shaun MItchem - Diggy starts to learn to walk, CC BY 2.0, https://commons.wikimedia.org/w/index.php?curid=4762045  Let us in this post try to elaborate on this Buddha vs Child Paradigm which Devesh coined for  differentiating between conventional IT systems and AI. It is essential to know the difference because it  helps in building the right kind of attitude towards implementing AI systems. A typical IT system such as  ERP does the job for what it was implemented. It is assumed that it will solve the problem for what it was  made. Take for example an accounting system like Tally. It will help you to manage your a

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 V(D, G) . The discriminator wants to correctly label an imag

This is a two part series on understanding Generative Adversarial Networks (GANs). This part deals with the conceptual understanding of GANs. In the second part we will try to understand the mathematics behind GANs. Generative networks have been in use for quite a while now. And so have discriminative networks. But only in 2014 did someone get the brilliant idea of using them together. These are the generative adversarial networks. This kind of deep learning model was invented by Ian Goodfellow . When we work with data already labelled, it’s called supervised learning. It’s much easier compared to unsupervised learning, which has no predefined labels, making the task more vague.  "Generative Adversarial Networks is the most interesting idea in the last ten years in Machine Learning." - Yann LeCun In this post, we’ll discuss what GANs are and how they work, at a higher , more abstract level. Since 2014, many variations of the traditional GAN have co