or subscribe with
Join 3,800+ readers for one email each week.
Digests » 43
this week's favorite
GIPHY is proud to release our custom machine learning model that is able to discern over 2,300 celebrity faces with 98% accuracy. The model was trained to identify the most popular celebs on GIPHY, and can identify and make predictions for multiple faces across a sequence of images, like GIFs and videos.
Instead, I found websites to purchase pre-built rigs like the Lambda GPU Workstation. The only problem: they cost $12,500. This is a great machine for top-tier state-of-the-art deep learning research, but not so great if you’re on a budget. That’s why I built my own version with similar or better components for $6200. To help other researchers, I’m sharing the details for every component so you can build one as well.
Here’s something that might surprise you: neural networks aren’t that complicated! The term “neural network” gets used as a buzzword a lot, but in reality they’re often much simpler than people imagine. This post is intended for complete beginners and assumes ZERO prior knowledge of machine learning. We’ll understand how neural networks work while implementing one from scratch in Python.
I’m going to tell a story: one you’ve almost certainly heard before, but with a different emphasis than you’re used to.
In my previous blog, I introduced the concept of combining a CNN with an LSTM to generate a caption of an image, and talked about how we are using this at Badoo to help our users find love. This time, we will explore how the incorporation of attention networks can help us improve on and enrich the captions that are generated by our model.