November Edition: Art & Data Science
8 Must-Read Articles
There are likely few among us who haven’t taken a look at a piece of artwork and stood in awe. I recently had the opportunity to experience this when I was in the Chicago Art Institute. As I stood in front of one of my favorite paintings of all time, Nighthawks by Edward Hopper, I could feel this raw energy coming out of the painting and enveloping me allowing me to connect with the artist. After that experience I started thinking about art in general and its many forms.
When asked “What is art?”, I’ve always had the tendency to jump right to paintings, drawings and photography as the answer. But I’ve realized my definition is too narrow. It’s much more encompassing to think of art as any visual, auditory or performance artifact that expresses the imagination and emotions of the artist while generating an appreciation for the beauty and emotional power of the artifact in an observer. Phew! That’s a mouthful of a definition!
“Art enables us to find ourselves and lose ourselves at the same time.” — Thomas Merton
The good news is this new definition opens up the world of art to data science. We might not think of it but each line of code we write could be a work of art! Even if that’s not the case, different techniques within data science have been applied across the world of art. This month’s edition focuses on exploring a variety of techniques across different artistic foci. We begin with my old definition and look at paintings, drawings and photographs. The uses of image processing begins with an introduction to using deep learning to detect forgeries, which leads us to opening the supply of artwork on the marketplace along with a recommendation system. From there we visit neural style transfer, long short-term memory models and apply them to two and three dimensional images. To cap off the image processing section, we take a look at how to make generative adversarial networks that create novel images.
The last three articles cover different areas of art: music, movies and design. In our look at music, we explore clustering based on the features of an artist’s music along with an in depth comparison of those features. The captions of movies were analyzed using natural language processing techniques to help the author learn a new language. The final article uses convolutional autoencoders to create a search engine for interior design and a sketch to image engine which is then applied to fashion and textile design. I hope you enjoy this selection as much as I did! Happy Learning!
Andrew DeCotiis-Mauro, TDS Editorial Associate.
Art connoisseurship in the age of machine learning
By Catherine Huang — 5 min read
As a Data Science newbie, I was intrigued by how real data scientists solve real-world problems. Reading many challenges posted on Kaggles, I was looking for insights on how these experts tackle the interesting competitions. One challenge that caught me by surprised me was the “Painter by Numbers”challenge. It asked the contenders to develop a program that can identify paintings by the same artist.
Data Science, Machine Learning and Artificial Intelligence for Art
By Vishal Kumar — 6 min read
Data Science, Machine Learning and Artificial Intelligence are fields from computer science that have already penetrated many industries and companies around the world. Their adoption is almost certainly correlated with the rise in “big data” over the last decade.
AI for artists
By Savio Rajan — 12 min read
The history of art and technology have always been intertwined. Artistic revolutions which has happened in history were made possible by the tools to make the work. The precision of flint knives allowed humans to sculpt the first pieces of figurative art out of mammoth ivory. In the present age , artists work with tools ranging from 3D printing to virtual reality, stretching the possibilities of self-expression.
Neural Networks and The Future of 3D Procedural Content Generation
By Sam Snider-Held — 8 min read
As a Creative Technologist at MediaMonks, a global production agency, people are always asking me about ML, AI, Neural Networks, etc. What are they?What can they do? How can we use them?
GANGogh: Creating Art with GANs
By Kenny Jones — 13 min read
Our primary motivation in studying GANs this semester was to try to apply a GAN-derived model to the generation of novel art. Much of the work in deep learning that has concerned itself with art generation has focused on style, and specifically the style of particular art pieces.
Spotify’s “This Is” playlists: the ultimate song analysis for 50 mainstream artists
By James Le — 15 min read
Each artist has their own unique musical styles. From Ed Sheeran who devotes his life to the acoustic guitar, to Drake who masters the art of rapping. From Adele who can belt some crazy high notes on her pop ballads, to Kygo who creates EDM magic on his DJ set. Music is about creativity, originality, inspiration, and feelings, and it is the perfect gateway to connect people across differences.
Leuk Taal: Learning a New Language Through Data Science (and Art)
By Rafael Pierre — 8 min read
When I started to learn Dutch, I felt amazed by how the language reflects how dutch people are mostly direct and objective. You will rarely see a dutch person creating excuses or embellishments for the sake of covering up, or pretending to like something or someone.
des.ai.gn — Augmenting human creativity with artificial intelligence
By Norman Di Palo — 6 min read
One of the most discussed aspects of artificial intelligence and computer science its whether machines can be creative or not. This discussion is as old as the first computer, but in recent times amazing results from Generative Adversarial Networks and similar architectures really made the discussion bigger.
We also thank all the great new writers who joined us recently, Jeremy S. Cohen, Robert Sandor, Dmitry Storozhenko, Chris Bow, ratama, Max Ghenis, Fábio Neves, Stacey Ronaghan, Billy Whalen, Satya Nugraha, Matt Moore, Shayaan Jagtap, Mandy Gu, Ankit Paliwal, Rico Meinl, Aditi Sinha, Amit Rathi, and many others. We invite you to take a look at their profiles and check out their work.
