This Blog Post Does Not Exist…Or Does It?

A quick overview of generative adversarial networks (GANs) — a type of artificial intelligence that are capable of generating, among other things, pretty realistic looking photos of humans that do not exist.

Shout out to those hard-working generative adversarial network (GAN)! Ok, I don’t really know about hard-working, but it is pretty cool. Let’s review.

Intro to GAN

GAN technology came out in internally at Nvidia, the computer graphics company, in 2014 and released publicly in 2018 (as StyleGAN). The studies are linked.

I’m not going to pretend I understand the details of either study. But based on the Wikipedia article linked above, what I can explain is that a GAN is the result of two neural networks that compete against each other, in one of those mathematical, strategy “games” researchers like to play.  The networks study photographs (or text) and then decide which elements to use to generate something new.

I think some people will find it creepy, but I think it’s cool. For the human photos, it’s hard to not project a humanity into the faces, even though, logically, these are people that have never existed. The generated fake people seem, somehow….special.

Here’s a quick intro to some GAN and some links to explore. Enjoy!


Explore Some Fake Stuff

As I said above, one of the possible outputs of a GAN can be a surprisingly realistic looking photographs. View some of them at thispersondoesnotexist.com. Every time you refresh, you get a new person that has never existed. It’s like dreaming for computers.

This github repository has a list of a few more websites of GANs that generate photographs of humans, fake rental ads, articles, anime, and more results that don’t exist. There are fake cats, but computers seem to have trouble with animals. I suggest not looking at them. (They’re creepy.)

Test Yourself, Human!

Some of these faces look pretty realistic. For instance, the image above-left is an “image of a young woman generated by StyleGAN, an generative adversarial network (GAN). The person in this photo does not exist, but is generated by an artificial intelligence based on an analysis of portraits.” The ad on the right is fake, too. Could you tell?

If you want to really test yourself, the website Which Face Is Real throws up 2 side-by-side images.

Catching up with Friends.

Unless you’re a dog cat on the internet, you can probably tell the difference (and probably even especially if you are a cat). The fake images have a few tell-tale signs like smudged backgrounds, odd looking teeth, unusual wrinkles, and some of them just don’t seem right.

You can also test yourself with the fake poems at Bot Poet.

Offshoots

Composites – There are some offshoots of the original technology, like this github repository which shows an example of a composite generated image using a StyleGAN image + an image of the Mona Lisa.

Digital “models” – I wouldn’t say these examples are quite the same, but there are already digital “models” on Instagram and in advertising campaigns. Lil Miquela has over 1.5 million followers on Instagram, and there’s a modeling agency specializing in digital “models”.

Video – The one below is uses around 8 frames of video to train their neural network, resulting in a real-time talking head model. It could be like one of those “deep-fake” videos, except the new heads are people that don’t exist. And you can kind of tell, if you watch the video below, human, the new heads do not really look too realistic (yet).

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

Statement regarding the purpose and effect of the technology
(NB: this statement reflects personal opinions of the authors and not of their organizations)

We believe that telepresence technologies in AR, VR and other media are to transform the world in the not-so-distant future. Shifting a part of human life-like communication to the virtual and augmented worlds will have several positive effects. It will lead to a reduction in long-distance travel and short-distance commute. It will democratize education, and improve the quality of life for people with disabilities. It will distribute jobs more fairly and uniformly around the World. It will better connect relatives and friends separated by distance. To achieve all these effects, we need to make human communication in AR and VR as realistic and compelling as possible, and the creation of photorealistic avatars is one (small) step towards this future. In other words, in future telepresence systems, people will need to be represented by the realistic semblances of themselves, and creating such avatars should be easy for the users. This application and scientific curiosity is what drives the research in our group, including the project presented in this video.

We realize that our technology can have a negative use for the so-called “deepfake” videos. However, it is important to realize, that Hollywood has been making fake videos (aka “special effects”) for a century, and deep networks with similar capabilities have been available for the past several years (see links in the paper). Our work (and quite a few parallel works) will lead to the democratization of the certain special effects technologies. And the democratization of the technologies has always had negative effects. Democratizing sound editing tools lead to the rise of pranksters and fake audios, democratizing video recording lead to the appearance of footage taken without consent. In each of the past cases, the net effect of democratization on the World has been positive, and mechanisms for stemming the negative effects have been developed. We believe that the case of neural avatar technology will be no different. Our belief is supported by the ongoing development of tools for fake video detection and face spoof detection alongside with the ongoing shift for privacy and data security in major IT companies.


Slightly off-topic, there’s a new Frontline documentary on AI. It’s 2-hours, so it’s a commitment. It doesn’t really go into the GAN-side of artificial intelligence, but it does discuss automation, privacy, and surveillance.

In the Age of AI FRONTLINE, from PBS. [1:54:16]

The documentary provides many reasons to be afraid of AI, particularly with regard to surveillance and use of AI by governments. We can’t really predict what governments will do, but if behavior control is a goal of AI there’s a natural user group: people who have trouble controlling their behavior. This would be people who have or have had issues or struggles with:

  • substance abuse
  • memory loss
  • chemical imbalances in the brain
  • adhd
  • neurological damage
  • loss of motor control

Or even just reminding people to eat better and go outside more. I’m sure there are more. Anyway, that’s my thought. Seems fair to be afraid, but also there are some opportunities that shouldn’t be overlooked.


And now on the cultural side : the trailer for Her. I don’t know if it’s possible to have an OS this advanced, but there are some interesting fantasy explorations in this movie.

Solving Design Problems like a Mathematician

While reading a forum discussion on FreeCodeCamp, I came across a reference to George Pólya’s book, “How to Solve a Problem”. In this post, I review Pólya’s problem solving strategy.

In a recent FreeCodeCamp forum, someone asked a question about journaling:

Hi coders,
While looking for the source for my project, I saw that some programmers or developers wrote a kind of diary to keep track of the code. I think it’s nice, but I was wondering exactly how you can structure a diary and if any of you use this to write code. Question here.

Good question. I’ve seen other people use diaries or online journals, or those things people use…writing logs or whatever. 🙂

Anyway, the only reply includes a link about using a “logbook”. On the link page, the author references George Pólya and his book How to Solve It. I had never heard of this person or his book, so I did a little research.

George Pólya, (1887 – 1985)

George Pólya was a Hungarian-born mathematician who was known for his mathematics work, as well as his work in heuristics. Heuristics is “any approach to problem solving or self-discovery that employs a practical method”.

“Examples that employ heuristics include using a rule of thumb, an educated guess, an intuitive judgment, a guesstimate, profiling, or common sense.”

He wrote a book about solving problems using common sense principles.

1st edition cover of “How to Solve It”, published in 1945, by George Pólya, a Hungarian mathematician.

The George Pólya Method of Solving Problems

The Wikipedia page shows that Pólya lays out some pretty good heuristics for solving problems. Although he intended for these strategies to be used for solving math problems, I think they could be used to provide a structured method for solving almost any difficult problem.

The Pólya problem solving method involves 4 principles:

  1. First, you have to understand the problem.
  2. After understanding, make a plan.
  3. Carry out the plan.
  4. Look back on your work. How could it be better?

So how does it work?

Principle 1: Understand the Problem

Pólya based the first principle, Understand the Problem, on the idea that math students struggled to solve problems due to a lack of understanding the problem in full or in part. His technique involved coaching teachers to prompt students with the following questions:

  • What are you asked to find or show?
  • Can you restate the problem in your own words?
  • Can you think of a picture or a diagram that might help you understand the problem?
  • Is there enough information to enable you to find a solution?
  • Do you understand all the words used in stating the problem?
  • Do you need to ask a question to get the answer?

Essentially one should not move past principle one until a constructive answer can be given. It’s not clear from the Wikipedia entry if a constructive answer is required for each question or the entire problem.

 Principle 2: Make a Plan

Basically he felt that a person gets better at selecting a good plan/strategy the more times they solve problems. Here’s a big list of strategies:

  • Guess and check
  • Make an orderly list
  • Eliminate possibilities
  • Use symmetry
  • Consider special cases
  • Use direct reasoning
  • Solve an equation
  • Look for a pattern
  • Draw a picture
  • Solve a simpler problem
  • Use a model
  • Work backward
  • Use a formula
  • Be creative – (“[Have] patience to wait until the bright idea appears”)
  • Applying these rules to devise a plan takes your own skill and judgement – (“Always use your own brain first”)

Principle 3: Carry out the plan

Simple enough, but the main problem people have with this step is giving up too soon. For that, the Wikipedia entry says:

“In general, all you need is care and patience, given that you have the necessary skills. Persist with the plan that you have chosen. If it continues not to work, discard it and choose another.”

Principle 4: Review, Reflect and Extrapolate

Take a look at what you’ve done, and evaluate how well it worked (or didn’t), and see how you can use what you’ve discovered for future problems.


Finding the book:

If you want to find this book, I recommend trying your library. I found it by searching for "how to solve it book pdf" (Google suggested the "pdf") and I found a copy.

Update:

An earlier version of this post included an account of how I applied Polya’s technique to my portfolio changes. A follow-up post will focus on that account.

Design Courses with Ellen Lupton on Skillshare

Ellen Lupton is a curator of contemporary design at Cooper Hewitt, Smithsonian Design Museum in New York City and director of the Graphic Design MFA program at Maryland Institute College of Art (MICA) in Baltimore. She is also the author of Thinking with Type, which is widely used in graphic design.

After recently browsing around on Skillshare, I discovered a few of her courses. Many are free and only around 30 min long. Here’s a short list. I haven’t taken them all, but I hope to review them sometime soon.

Typography That Works: Typographic Composition and Fonts

Screenshot from skillshare

 

 

 

Demystifying Beauty: Inspiration for Design

scrreenshot

 

 

 

 

Graphic Design Basics

Screen shot of video on scale

 

 

 

How Posters Work

Title slide for skillshare

 

 

 

 

I’m not a big fan of the Skillshare interface — for one thing, the videos autoplay when you load the page. But, these are pretty short videos, about 30 minutes, so don’t let autoplay scare you. Plus, they’re all free.

Typography Book Projects: Psychogeographical Mapping, Cooking & Typography

Outlining some ideas for my typography class at Parson’s, for our book making projects.

For class, we will be creating 2 projects, which will turn into books. One is a psychogeographical map and the other is a little cooking memoir. I need to come up with idea for each.

The cooking book is to teach us about book binding and selecting type options for recipes, which can have many options. We need to pick a somewhat personal story/recipe. I think I will write about both my hatred of pot pies, as well as my love of Gordon Ramsay’s shepherd’s pie recipe, which I first made during Hurricane Sandy. This was also the week I adopted my cats, only kittens at the time, only 8-10 weeks old. At the time, the subways had been shut down, so I couldn’t go anywhere for a week. Luckily, because I was living so far north in Manhattan, there was no flooding and basically we didn’t lose any power. (In the East Village, it was another story.) I think there’s enough there to write a good story.

For the Psychogeographical Mapping…I’m drawing a blank. Some ideas:

  • dog runs
  • pet stores
  • Japanese grocery stores
  • Walking down the street listening to Rhapsody In Blue and taking note of what’s around me. (If you haven’t done this, while taking a walk in NYC, you’re really missing out.)
  • Mapping the Central Park Conservatory Garden, a good place to read. Maybe the benches.

Maybe some better ideas:

  • Map movie theaters in NYC that aren’t chains, up to 96th St. Meaning no Regal, AMC, or Imax theaters. City Cinemas is OK.
  • Map Goodwill Donation stores. I do go to Goodwill and the Salvation Army a lot.

I’m leaning towards the theater idea. Now to do some write-ups.