Variational Autoencoders (VAE) are really cool machine learning models that can generate new data. It means a VAE trained on thousands of human faces can new human faces as shown above!
Recently, two types of generative models have been popular in the machine learning community, namely, Generative Adversarial Networks (GAN) and VAEs. While GANs have had more success so far, a recent Deepmind paper showed that VAEs can yield results competitive to state of the art GAN models. Furthermore, VAE generated images retain more of the diversity of training dataset than GAN counterparts. Continue reading An Introduction to Variational Autoencoders→
Let’s have a look at this god-tier math puzzle. Only one out of seven gets it right, and the other six don’t. So, what are the odds for solving it correctly? 1 to 6. Generally, if \(p\) is the probability that someone will get it right, then his/her odds are \(p/(1-p)\).
However, it isn’t necessarily true that \(p=1/7\) for every person because some people are smarter, some have better education and so on. Hence, \(p\) also depends on the person attempting the puzzle. In a Bayesian framework, we capture this dependence with conditional probability.
My mistress’ eyes are nothing like the sun;
Coral is far more red than her lips’ red;
If snow be white, why then her breasts are dun;
If hairs be wires, black wires grow on her head.
I have seen roses damask’d, red and white,
But no such roses see I in her cheeks; Continue reading A Week of Poetry: Day 3→
This is a very unusual post for this blog. I hope my regular readers will bear with me.
I love Game of Thrones. I have read the books and the companion novels. I have been following the series for years. I am familiar with most of the fan theories too. Tonight the series finale aired. I didn’t like how the show ended. It felt rushed and very baffling. Continue reading How Game of Thrones Should Have Ended→
The distribution of primes plays a central role in number theory. The famous mathematician Gauss had conjectured that the number of primes between \(1\) and \(n\) is roughly \(n/\log n\). This estimation gets more and more accurate as \(n\to \infty\). We use \(\pi(n)\) to denote the number of primes between \(1\) and \(n\). So, mathematically, Gauss’s conjecture is equivalent to the claim
Is it possible to design a machine that detects lies? Sure, people have already built devices called polygraphs that monitor blood pressure, respiration, pulse etc. to determine if a person is giving false information. However, that is not same as “detecting lies” because polygraphs merely measure physical effects of telling lies. On the top of that, they are hella inaccurate. I am talking about REAL lie detectors, ie. machines that can instantly validate the statements themselves. Can we actually make such machines? (*insert new startup idea*) Continue reading Lie Detectors and the Story of Halting Turing Machines→