Student Area

axol-GPT2

After playing around with GPT2, I noticed with certain phrases it can generate full on news report style articles (even with authors and the proper formatting) which it thought was pretty interesting. I fed it some political slogans or common sentence starters and it generated this sci-fi showdown announcement which is hilarious.

This Saturday, the first ever Octagon women’s featherweight bout will go down in the main event of UFC 216. Cris ‘Cyborg’ Justino will make her long-awaited Octagon debut, as she faces bantamweight champion Amanda Nunes. Amanda Nunes vs. Cris Cyborg — Title Bout Nunes will likely be fighting for the UFC bantamweight title when she enters the Octagon with Cyborg, but she wants to defend the belt against both her nemesis, Ronda Rousey, and Cyborg.
-----------------------------------------------------------------------
Trump's departure from the white house will happen this Friday at around 3:00 pm. Instead of being in Washington, he will be in New Jersey, on a working vacation. 

WHCD: Who should replace @POTUS at the White House Correspondents Dinner? — The White House (@WhiteHouse) September 17, 2017 

[Video via Fox Business]
-----------------------------------------------------------------------
This is New York Times reporter Johnny Sharpie, bring you this report from Pittsburgh, PA.  (BEGIN VIDEOTAPE) 
JOHNNY SHARPIE, REPORTER: We're walking towards this massive firehouse. 
UNIDENTIFIED MALE: What's that sound? 
SHARPIE: Oh, that's fire, sir. 
UNIDENTIFIED MALE: Oh, thank you, sir. 
SHARPIE: Back here. 
UNIDENTIFIED MALE: Come on, everybody, come on. 
SHARPIE: OK, well, just a second, sir. We're coming from a second floor, sir. The fire just went back there. 
UNIDENTIFIED MALE: Alright. Yeah, back here. 
UNIDENTIFIED MALE: All right, all right, we're all the way around

axol-LookingOutwards04

http://www.aiartonline.com/art/holly-grimm/

https://hollygrimm.com/acan_final

hollygrimm_ny_dieb201_3840 (1)

hollygrimm_pilar_bn178_3840 (1)

The project was done with additional constraints from a neural network trained on art composition attributes. It’s attempting to take traditional fine art concepts (Variety of Texture, size, color, shape, contrast …) and embodying them as a part of the constraints.

What fascinates me most about this project is the documentation in the second link. The documentation showed every step and the different passes of images through the model, the different dimensions of values that was modified to produce the look which I though was really cool. It’s interesting to see how some traditional concepts like color theory and textures gets replicated/translated into digital, machine learning space– and also just how the categorization of human art work fits into the listed categories.

gregariosa-LookingOutwards04

Ross Goodwin’s project is an AI literary road trip, where he drives around a text generating model that writes a novel based on what it sees through a camera. Through his work, he posits that artificial intelligence assists creatives to produce artwork, rather than replace them, as humans find more ways to collaborate with the AI. I was fascinated by this work, as we often think of machine learning models as static tools, spitting out results based on existing datasets. For this project, however, the AI is, in some sense, ‘experiencing’ the data together with the human, bringing into question the degree of entity it has. His choice to drive the model around through the trip, rather than showing an hours long video clip and gps data, seems profound, and the resulting text is also pretty interesting.

thumbpin-TeachableMachine

I wanted to try using Teachable Machine to detect different letters of the ASL alphabet. I realized that I needed to add more input images with my hand in different places (e.g. in the top left/right corners, in front of my face, closer to the camera) for better output.

lampsauce-TeachableMachine

I trained a model (view here) to detect if someone is properly wearing a mask or not. It’s a huge pet peeve of mine when someone is wearing a mask, but their nose holes are out, defeating the purpose of the mask. The classes the model detects are mask on, mask partially off, and mask off.

I originally tried to make a model detect if I was wearing different kinds of glasses, but I think that was too nuanced.

 

gregariosa-TeachableMachine

I created a “rock, paper, scissors” model using this tool. While this was a lighthearted exercise, it revealed how training ML data requires human touch to be most successful. When my idea initially emerged, I instantly thought the images would look like stock photo representations of ‘rock, paper scissors’, where the silhouette of the signals are recognizable to a human eye. However, when training the model, I found myself using natural gestures of rock paper scissors, resulting in many unrecognizable gestures visually. This made sure that the model was more accurate when interacting with it on camera, which was perhaps not achievable if the model was just made of stock photo images of rock paper scissors.

thumbpin-ArtBreeder

3 images made with the general model:

1 image made with the album cover model:

I was surprised by how much I liked some of the generated images. I thought some of them were really exciting, which was unexpected.

gregariosa-GPT2

The storytelling ability of this tool was really impressive. In example 1, I started a stereotypical love letter that ended up becoming an inundation of cringey confessions.

1.

Dear love,

My good golly woman, I hope you’re doing well. I miss you the most on this cold winter day. I yearn for the touch of your hands and that warm smile upon your lips. I think about your face more and more these days. What are your plans for the day? Do you have a favorite park where you like to lay in the sun? Are you holding someone special in your arms? Do you get to sing praises to God and have that one-of-a-kind moment with Him today? What’s your joy today, my dear?

Oh Lord, I love you so much and I’m feeling so lonely. You always give me the strength to go on. Don’t let my spirit be broken today. My heart aches to just be

In example 2, I tried to challenge whether the tool can recognize gender neutral pronouns. While the story itself was quite convincing (except the random “ALSO READ: Want to attract a good man? Try this,” which probably came from an ad), the tool wasn’t able to maintain the “they/them” pronoun into the second paragraph.

2.

Alex was livid. They stormed outside the cafe and left for the beach to calm down. They could not bear with the fact that this lady was happy with her partner and had a birthday party the very next day without their knowledge.
ALSO READ: Want to attract a good man? Try this
Alex pleaded with her to pay him the money, that she had been swindled. He said he would take the family to another cafe and raise the money to be paid to them. He tried explaining that they had spent the previous week on a fishing expedition at a neighbouring beach, where they spent a fortune. He told her they had planned to spend the

 

thumbpin-Pix2Pix

I wanted to see how Pix2Pix would generate images from sketches that do not look like cats. One of the things I tried drawing initially was a snake, it really did not turn out.

miniverse-lookingoutwards4

I chose this project:

https://artsexperiments.withgoogle.com/runwaypalette

Where Google Lab worked with  Business of Fashion to grab and clusters thousands of color palettes seen on fashion runways. I could stay on this site for days. I love fashion and this site has inspiration organized in an interesting way. Normally users go through different runway lines by designer, but this color palette organizational style is useful to laymen rather than designers.

(small comment: whoever trained the machine learning model to pull the color palettes did not teach it to ignore skin color and this biases the entire color space to neutral tones)

Here is the entire color space:

 

 

 

 

 

 

 

 

 

 

Here is an example palette: