Hands-on Tutorials

Creatives and AI collaborating: how a trained pix2pix model can help with colorization

Results highlights from using pix2pix to help colorize historical portraits from the Smithsonian’s National Portrait Gallery (figure by author)

Humans are inherently creative. New tools unlock the creativity lying dormant in an untapped wave of makers that find unexpected ways to showcase their artistic abilities. According to a Pfeiffer Consulting study, even experienced artists appreciate new tech as an enabler of creativity. The study found that 74% of the artistic process, from envisioning a work of art to its realization, consists of tedious steps that many artists wouldn’t mind automating. This is where some artists feel that machine learning can be of assistance. As an amateur artist myself with graduate training in machine learning, I’ve been exploring this possibility…


Using Latent Dirichlet Allocation to Extract Underlying Trip Topics from GPS Trace Data

Visualizing LDA extracted trip topics, figure by author

Every text is produced by an author whose utterances, units of discourse exerted with intent, are preserved in writing. As such, large collectives of texts can be used to study pieces of culture. Unsupervised machine learning methods like topic modeling allow us to extract underlying cultural themes from large volumes of text data. With big data growing in the transportation field, a new analysis opportunity arises and researchers can seek to extract meaning and culture from traces of mobility.

When evaluating new transportation modes in cities, local government leaders and city planners may wonder what types of trips users generally…


Using CycleGAN and Google’s QuickDraw dataset to create festive dragons and oxen

CycleGAN dragon outputs (image by author)

Friday, February 12th marks the start of the Lunar New Year in 2021. You’ll often see colorful dancing dragons at new year festivals wishing celebrators good luck. To celebrate ML-style, I used CycleGAN to generate dragons with fun decorative flare (shown above) and I’ll describe the implementation steps in this article. Perhaps these GAN-generated dragons will also bring luck! In Cantonese, we say “Gung Hay Fat Choy” to wish you happiness and prosperity in the new lunar year. I never miss an opportunity to use cheesy puns, so GAN Hay Fat Choy! 🙈

The CycleGAN paper was written by researchers…


Testing the potential of using deep learning to measure brand recognition

Photo by Kate Torline on Unsplash

With the popularity of visual social media platforms such as Instagram, brands capitalized on this trend, using these platforms as a means to advertise using their own brand imagery. Users often consume this form of advertising one image at a time while scrolling through their feeds. In this seconds-long window, brand marketers must capture the attention of a potential consumer with a memorable image that speaks to their brand. I was curious about how brands compare and as computer vision enthusiasts do, I used CV to investigate.

Convolutional neural networks (CNN) have been shown to perform comparably to human vision…

Tina Tang

Writing about exploratory work applying ML/DS creatively. (she/her) Twitter: @StocasiaAI

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store