08 – Page 3 – 60212: INTERACTIVITY & COMPUTATION

lsh-MachineLearningA

Pix2Pix

The edges2cats filter was interesting to play with in regards to how it dealt with line and scale. Large open spaces were filled with texture, while finer, smaller detail led to a blurry mess.

The facades felt more ambiguous in output oddly enough. Maybe due to the Mondrian style of partitioning the UI requires.

GAN Paint

source: Carnegie Mellon University College of Fine Arts Facebook

When working with the default image, the effects were immediate no matter what tool I used. When I uploaded my own image, the effects became much harder to tease out.

Artbreeder

Artbreeder is always a lot of fun, given the sheer amount of content one can generate within the tool. I do occasionally consider it through the following lens though:

A friendly reminder that Ganbreeder is just one drilling platform into #BigGAN's treasures. So whatever you pull out there might already be claimed by some independent prospectors from the other end of the latent space. pic.twitter.com/ZPGrJJsvVJ

— Mario Klingemann (@quasimondo) March 11, 2019

Infinite Patterns

GPT-2

Do you know who I am?

You see, this is where things get a little confusing. I'm a lot more than I let on as a person.

Let me explain.

First, I'm not a monster.

Second - and this is important because it has implications for my next step - I'm the kind of person who is able to change.

Change is not the same thing as changing a person. A person can make a life-long change in such a short time that the change is invisible - it's not part of the world they know or understand or know how to interact or have compassion for.

Changing a person is hard; you're making the change for the sake of yourself and others.

And that's hard.

The best way I've found to change was in what I didn't know I was capable of.

It wasn't that I wanted to change, it was that I knew I couldn't change, and so I made a choice - a good, thoughtful choice - to not learn the lessons I could

What's love got to do with it? Well, like it's a question that's been answered many times over, it's an all-encompassing question that goes a number of ways and there is no right or wrong answer.

But for those who want to know, the answer starts with a simple premise:

"You should love everyone you meet."

And why would you want to say something so obvious and easy to say? Well, perhaps you need some extra help when it comes to saying it or you fear other people don't really know what they're doing when it comes to the most basic human needs... or maybe you can't quite make the case that it's not a simple idea, even though you know it to be so. But the good news is that once you say it, it's there for everyone to understand and respect, so there's really no reason to fear or deny saying it.

I'd argue that this simple premise applies to any relationship for both men and women so even if you're not ready for it right away, there can be no better idea

I usually don't think of AI as being used for a stylistic decision like font making, so I was curious to see what pairings the system suggested.

A. Pix2Pix

I spent some time on Edges2Cats making people's fursonas.

This tool is lots of fun, but frustrating to use because of the discrepancies between how humans interpret edges and how an edge detector does. Connie suggested that I look at the original inputs (edge detections of cat photos) to see what arrangements of edges produced what output. This technique was necessary to understand how a cat nose/mouth was generated. As such, all my drawings have a very pronounced upper lip area to force the cat mouth to appear.

Here are facades of windows within doors, and an image of a dark future where humans are the handbags of omnipotent AIs.

B. GANpaint studio

GANpaint was probably the most frustrating tool in this assignment, but I think it has a lot of potential! Currently, the lack of layers you can 'paint' with and the very low resolution output limit what you can create. I assume that as the encoding of semantic features becomes better understood, more features will be available to manipulate in later demos.

C. Artbreeder

I have spent so much time on Artbreeder that I don't even know what to say about it! The new Portraits category is very frustrating (I can't understand what the sliders actually encode) but in a way that makes me want to spend more time with it. I tried to make myself, but it didn't turn out very well. Other people have made amazing Danny Devitos and Elon Musks.

Here is my Artbreeder profile if you want to see all my creations.

D. Infinite Patterns

E. GPT-2

That was the funnest hour of my life so far. All original text came from humorous online posts, it is not mine.

F. Google AI Experiments

I played Semantris for a couple of rounds. Perhaps it was not the most creative use of my time, but I enjoyed it a lot. It made me wonder if I was contributing training data to something. The most obvious answer would be a semantic mapping algorithm. It would be interesting if destroying multiple connected blocks required you to relate the two words in a clue.

zapra – 08a – machinelearning

Pix2Pix

This was a really fun way of seeing the different opportunities to interact with machine learning from the user's perspective. I love all my cats.

GAN Paint

This reminded me a lot of the stamp tool in Photoshop. The examples given are all architectural, but I think it would be interesting to see this being used on people or other living things.

Artbreeder

I had a lot of fun creating my own mix of genes (see a chicken-catamaran hybrid below).

Infinite Patterns

I created this using the seal + stone wall + African Grey Parrot crossbreed I had made in ArtBreeder.

Talk to Transformer

This was my favorite one to play with by far. My first several attempts were too vague to generate anything of interest, but its funny to see how many specifics you need to feed the transformer to get a satisfactory amount of coherent nonsense.

I had this crazy dream about zombies last night where we were all in the same room together." He smiled. "I don't remember if I was the one who said 'we' that time or whether it was the other guests or the other staff, but we were all feeling weird when we woke up to discover that we would soon be fighting for their lives against these horrible creatures."

"Yes, I remember," her father replied with a small smile. "It was a good dream." He reached for a drink of water, but hesitated when he heard the sound of water dripping down the hallway below, then he looked down the hallway to see that three of the four staircases had collapsed on their own.

Harry sighed. With one hand pressed to his forehead, he reached for the drink in the bowl and took a sip. "What Can I tell you a secret about why I am afraid of birds? I am afraid of birds because, like all things that live in the sky, they have eyes. And I fear that their eyes are in the sky and their eye-screens are on and I can't tell them anything except what their own eyes can see. And so I fear their eyes like a mother afraid of a baby. And I know they will hurt me.

"What if one day, one of them looks up and sees me, I am so afraid of being hurt so I put a glass of water on the stove and sit there, so that they can't reach me. They are too smart, too clever or there is some mistake. So, even if they know every part about me that has not been invented, they will never hurt me. And sometimes they seem to be watching the moon."

He paused and then added: "And sometimes they are thinking how to tell this to their offspring. They are already thinking too much, but I am only a child, and they have the power of children."

The woman laughed and said happened?" he asked.

"When we arrived at the conference, we found out that the hospital was closing down until further notice while the owner decided to leave the building entirely." Her father replied as he sipped from the cup. "And the next time you arrive

----------------------------------------------------------

2. Can I tell you a secret about why I am afraid of birds? I am afraid of birds because, like all things that live in the sky, they have eyes. And I fear that their eyes are in the sky and their eye-screens are on and I can't tell them anything except what their own eyes can see. And so I fear their eyes like a mother afraid of a baby. And I know they will hurt me.

He paused and then added: "And sometimes they are thinking how to tell this to their offspring. They are already thinking too much, but I am only a child, and they have the power of children."

The woman laughed and said

Google AI: Magic Sketchpad

Here's a sketchpad on glitch that will try to finish your drawings for you. It's cool when its accurate and endearing when it scribbles haphazardly.

sovid – ML Toe Dipping

edges2cats

I found it interesting to see how the algorithm distinguished a nose from an eye, especially in sketches that weren't trying to resemble a cat.

GanPaint

original:

new:

ArtBreeder

and ocean in the field

french horn funghi

I found this really useful for character design in the portrait mode - you could create a whole family of people that were clearly related from one photo.

Infinite Patterns

original:

new:

TalkToTransformer

GoogleAI

I played around with the "How New Yorker are You" experiment, in which two players compete to be crowned the realest New Yorker by answering questions based on tweets that originated in NYC from the past year. The closer your responses are to the topic--and the faster you respond--the higher you score.

ilovit – MLtoedipping

Pix2Pix

I tried to make a dog cat.

It's interesting how tiny gestures can greatly affect the certainty of the resulting image, and what it interprets as negative or positive space. I tried pretty hard to get it to interpret lines as certain things

GANPaint

It took me a little while to figure out that the painting here can only really alter an already existing element so that it becomes something else, and not really create new elements in most cases. It's also interesting how the generated fields always seem more flat than the original image.

ArtBreeder

General:

Portraits:

The set of portraits to crossbreed with are almost all really attractive people. It is kinda hard to make a portrait without beautiful eyes. The genetic metaphor is apt - you can almost guess what parts of each image are the result of what "ancestor."

Infinite Patterns by Alexander Mordvintsev

GPT-2

Eight years ago, when I was studying to convert but hadn't yet been to the mikveh, I experienced Simchat Torah for the first time. I had successfully 《reconciled to God. That's all the conversion I have to tell. I was on Shabbat observing the service with an older Jewish friend and he mentioned that he would be joining us the next day. When I entered the service, I sat in the front row as the rabbi took our seats. As he began his service, I saw him and, after a moment, I was shocked. Instead of holding the Torah over his head and repeating the name of the Lord, as a Hasid or Rabbi would do, he placed it in front of him over his right hip and the congregation began to pray. I looked at him. I thought to myself, This is a Hasidic man. What is he doing. I didn't know how to respond because it was completely unfamiliar. I said to myself that I just wasn't prepared to be a Hasid, to be surrounded by Orthodox people, to have a large group

"No, Shirley!" I cried as she began to climb over the bed and then started into the chair again.

"If it is too much trouble don't say anything," she said, still sounding like Shirley.

"I may not want to," I promised, "but I can't help it, can I?"

"Yes," she said, and I was quite sure she sounded disappointed.

Sitting there, staring at the empty window and the uninviting sunlight, Shirley sighed.

"Why, why, it's so nice out here!" she protested. "This is our house, after all, and our people, our house! I don't know what to do any more! I feel so empty like this."

"No," I insisted. "This is not our house... it's not my house."

"Oh, of course it is!" she cried. "You don't know what it means to stay on good ground. You have to! But it's time you did."

Google AI Experiments

It rarely correctly guesses what you're drawing. You start to notice after a little while what the typical graphical representation of the thing being drawn seems to be. Sometimes it's not the image I have in my head of the thing.

https://magenta.tensorflow.org/assets/sketch_rnn_demo/index.html