Image Augmentation for Deep Learning using Keras and Histogram Equalization
By Ryan Allred – 12 min read.
Deep Neural Networks, particularly Convolutional Neural Networks (CNNs), are particularly proficient at image classification tasks. State-of-the-art CNNs have even been shown to exceed human performance in image recognition.
GANGogh: Creating Art with GAN
By Kenny Jones – 13 min read.
The work here presented is the result of a semester long independent research performed by Kenny Jones and Derrick Bonafilia (both Williams College 2017) under the guidance of Professor Andrea Danyluk. The code associated with this project can be found at https://github.com/rkjones4/GANGogh.
Can a deep neural network compose music?
By Justin Svegliato – 9 min read.
When I first started grad school last September, I wanted to jump right into the deep learning craze as soon as I could. While I was working as a software developer in NYC, I kept hearing amazing things about deep learning: DeepFace could recognize people’s faces just as well as you and I could, AlphaGo was destroying players in a game that originally seemed elusive to AI, and GANs were just starting to gain momentum.
Predicting Logic’s Lyrics With Machine Learning
By Hans Kamin – 9 min read.
Logic has been a remarkable influence on my life since middle school, when I heard his song "All I Do" for the first time. The mixtape this song belongs to, Young Sinatra, singlehandedly made me a fan of hip-hop in all its forms, introducing me to styles old and new that I had otherwise never even considered listening to.
Hacking Data Art at an AI Genomic Hackathon
By Kristin Henry – 7 min read.
A while ago, I noticed an interesting hackathon was coming up. The AI Genomics Hackathon focused on a rare disease (NF2). Yes, I had promised myself that I wouldn’t do any more hackathons, but this was too hard to resist.
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? This post represents the first in a series I will be writing exploring the space where AI, Creativity, and 3D content meet.
Montreal painted by Huang Gongwang: Neural Style Networks
By Gabriel Tseng – 6 min read.
A really cool application of CNNs (convolutional neural networks) recently has been to style neural networks; these involve isolating the style of one image, the content of another, and combining them.
Pytorch Implementation of Perceptual Losses for Real-Time Style Transfer
By CeShine Lee – 6 min read.
In this post I’ll briefly go through my experience of coding and training real-time style transfer models in Pytorch. The work is heavily based on Abhishek Kadian’s implementation, which works perfectly Fine. I’ve made some modification both for fun and to be more familiar with Pytorch.
We also thank all the great new writers who joined us recently Garrett Kinsman, Manish Bahl, [Vihar Kurama](None), Joseph T. Hasselmann, Egor Dezhic, Yong Sheng Soh, Siavash Fahimi, Veda Konduru, Sam Snider-Held, Tomek Roszczynialski, Gidi Shperber, Dave Sotelo, Hank Stoever, Murat Vurucu, Seth Weidman, Maruti Techlabs, Armin Oliya, Wolf Garbe, Kirill Danilyuk, Noah Moroze, James Densmore, Dima Shulga, Devansh Lala, Paul-Louis Pröve, Pradeep Menon, Vihar Kurama, José Miguel Hernández Lobato, Susan Li, Kumar Shridhar, Hans Kamin, Elisha Terada, Justin Svegliato and many others.