"Orchestrating Game Generation" - by @yannakakis et al: http://yannakakis.net/wp-content/uploads/2018/10/orchestrating_game_generation.pdf #ML #Generative #Games
tag > ML
-
-
"IGNOR: Image-guided Neural Object Rendering":
http://niessnerlab.org/projects/thies2018ignor.html #ML #Generative -
Mask-pose Cascaded CNN for 2D Hand Pose Estimation from Single Color Images: https://www.yangangwang.com/papers/wang-mcc-2018-10 #ML
-
"Attention and Memory in Deep Learning" - new lecture by Alex Graves from DeepMind. #ML
"Unsupervised learning and generative models" - new lecture by @shakir_za:
-
Polyworld: Using Evolution to Design Artificial Intelligence (2007, by Larry Yaeger) - talk by Virgil Griffith
This presentation is about a potential shortcut to artificial intelligence by trading mind-design for world-design using artificial evolution. Evolutionary algorithms are a pump for turning CPU cycles into brain designs. With exponentially increasing CPU cycles while our understanding of intelligence is almost a flat-line, the evolutionary route to AI is a centerpiece of most Kurzweilian singularity scenarios. This talk introduces the Polyworld artificial life simulator as well as results from our ongoing attempt to evolve artificial intelligence and further the Singularity. Polyworld is the brain child of Apple Computer Distinguished Scientist Larry Yaeger, who remains the primary developer of Polyworld:
-
Selling property in latent spaces is a fascist agenda.
Generative IP is end stage madness. -
If GAN-Art has proven anything, it is that Humans can have a strong emotional reaction to a statical distribution - to the point of suspending disbelieve and irrationally attributing creative agency to a tensor of numbers. Magical thinking in age of AI?
-
#Prediction: Guided/Narrated explorations of waste generative latent spaces will be a mainstream form of entertainment in the 2020 - more popular than watching people play games on Twitch in 2018.
Mario Klingemann: https://twitter.com/quasimondo/status/1064248673683554305
Found a hideaway in the wastelands of BigGAN
I am in luck. Last night's sandstorm has brought a flock of Tumbleweasels right into my camp. These spherical mammals can travel over hundreds of miles just using the force of wind.
#ML Generative
-
"i asked a neural network to generate interpolations between a pomeranian and a pomegranate and accidentally fell in love" - emmaGANma #ML #Generative
-
Human-centered AI: a Case for Cognitively Inspired Machine Intelligence - Fei-Fei Li: #ML
"It is estimated that humans by the age of 6 are able to recognise 30'000 categories of objects"
"A discrete list of objects is not what the human visual systems gets when you open your eyes - in fact, its the interaction, the relationship between objects, people and actions that really define our rich visual experience."
Visual Genome: "a dataset, knowledge base - an ongoing effort to connect structured image concepts to language": http://visualgenome.org/
4 Future Directions for Visual Intelligence:
"I hope to see the next generation of AI tech will be more inspired by human intelligence - by Neuro, Cognitive & Behaviour science"
"The goal of AI should be benefiting humanity, should be enhancing humanity - not replacing it"
-
https://www.humtap.com - "AI-Driven Social Music Creation" #ML #Generative #Music
-
Interactive Machine Learning: How Machines Learn Best from Humans - talk by Charles Isbell:
"For the students in the room i should say, when ever you are giving a talk you should always have at least one slides with complicated equations that you don't explain - so people know that you are smart. I have 3, so people really know i'm really really smart" - @isbellHFh
-
Mubert: "an AI-based streaming service that creates royalty-free background music in realtime": http://mubert.com/ #ML #Generative #Music
-
"Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop":
https://dl.acm.org/citation.cfm?id=3025453.3025780 #HCI #ML
-
The Sound of Pixels: http://sound-of-pixels.csail.mit.edu/ #ML #Generative
"system that learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel" -
Co-Creative Level Design via Machine Learning: https://arxiv.org/pdf/1809.09420.pdf #ML
-
"Creating New Technologies for Companionable Agents to Support Isolated Older Adults": https://dl.acm.org/citation.cfm?id=3213050 sans-paywall: http://sci-hub.tw/https://dl.acm.org/citation.cfm?id=3213050 #ML #HCI
-
"Recent Research Advances on Interactive Machine Learning": https://arxiv.org/abs/1811.04548
"Learning Shaping Strategies in Human-in-the-loop Interactive Reinforcement Learning": https://arxiv.org/abs/1811.04272 #ML #HCI
-
All machines which humans teach to learn, should learn to teach humans.
