Kyso Weekly: Issue #7
You know the drill! Have a read of the latest & greatest and support your fellow data scientists by giving the studies you like a star!
Since 2014, GANs have exploded into a huge research area, with massive workshops, and hundreds of new papers. Compared to other approaches for generative models, they often produce the highest quality samples but are some of the most difficult and finicky models to train. In a GAN, two different neural networks are built. The first is a traditional classification network called the discriminator. The other network is called the generator. In this study the author takes us through GAN, explaining how to build models which generate novel images that resemble a set of training images.
Here the author expands on a previous study on the physical intuition behind the derivative of a polynomial function, and continues the series by attempting to work out the derivative of a trigonometric function. Motivation: Given a trigonometric function like f(x)=sin(x), how do we find it’s derivative? Click on the link above to find out how to do just that, in python.
In this short but interesting notebook, the author provides a brief intro to the NAND programming language. The NAND programming language was designed to accompany the upcoming book "Introduction to Theoretical Computer Science". This is an appendix to the book, which is also available online as a Jupyter notebook at this repository on Github.
In this study the author shows how one can compare the exam results of two different groups of students at different institutions taking two different exams (ACT vs the Iowa Test of Educational Development or ITED). The question is how to link the ACT score to an equivalent ITED score, so that we can better understand and have a better comparative overview of the entire distribution of test scores. Which students are actually scoring better?
That is all for now!! Have a great week!!