What’s linked is the official PyTorch implementation of a paper published in April of this year called Bringing Old Photos Back to Life.

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces.

The results are impressive!

Here’s a new acronym for you: Generative Teaching Networks (GTN)

GTNs are deep neural networks that generate data and/or training environments on which a learner (e.g., a freshly initialized neural network) trains before being tested on a target task (e.g., recognizing objects in images). One advantage of this approach is that GTNs can produce synthetic data that enables other neural networks to learn faster than when training on real data. That allowed us to search for new neural network architectures nine times faster than when using real data.

Fake data, real results? Sounds pretty slick.

Colin Lecher reporting for The Verge:

Last week, Gov. Gavin Newsom signed into law AB 730, which makes it a crime to distribute audio or video that gives a false, damaging impression of a politician’s words or actions.

While the word “deepfake” doesn’t appear in the legislation, the bill clearly takes aim at doctored works. Lawmakers have raised concerns recently that distorted deepfake videos, like a slowed video of House Speaker Nancy Pelosi that appeared over the summer, could be used to influence elections in the future.

This is the first (but likely not the last) piece of legislation aimed at fighting the potential impact of GANs Gone Wild.

It’ll be interesting to watch this game play out. I think the only long-term, sustainable solution will emerge from the same arena where the problem began: technological advances.

This isn’t just an awesome list of resources. The repo IS the resource! If you click through and the content is a bit too dense, start with the latest episode of Practical AI where Daniel and Chris explain many of these concepts in detail.

The latest machine learning research from my friends at Fast Forward Labs. Shiou Lin Sam and Nisha Muktewar teach us what meta-learners are and how they learn.

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.

Give it a try on the demo page or download the model yourself and follow along with the examples.

Person re-identification (re-ID) can be viewed as an image retrieval problem. The emergence of this task can be attributed to 1) the increasing demand of public safety and 2) the widespread large camera networks in theme parks, university campuses and streets, etc. Both causes make it extremely expensive to rely solely on brute-force human labor to accurately and efficiently spot a person-of-interest or to track a person across cameras.

Based on PyTorch.

Daniel and I talked about this AI painting on Practical AI #18 a few weeks ago. At the time the painting was expected to yield $7,000 - $10,000 US.

Since then, Christie’s held an auction, and the Portrait of Edmond Belamy sold for an incredible $432,500 US.

Finish him!

The purpose of this project is to provide a shortcut to developers and researchers for finding useful resources about Deep Learning for Natural Language Processing.

Organized by papers, datasets, courses, books, blogs, tutorials and more…

PyTorch is a flexible deep learning framework that allows automatic differentiation through dynamic neural networks (i.e., networks that utilise dynamic control flow like if statements and while loops). It supports GPU acceleration, distributed training, various optimisations, and plenty more neat features. These are some notes on how I think about using PyTorch, and don’t encompass all parts of the library or every best practice, but may be helpful to others.

How do you you teach a neural network to code? One screenshot with matching HTML at a time. 😂

Within three years deep learning will change front-end development. It will increase prototyping speed and lower the barrier for building software. The field took off last year when Tony Beltramelli introduced the pix2code paper and Airbnb launched sketch2code.

Currently, the largest barrier to automating front-end development is computing power.