Imagine This! Scripts to Compositions to Videos: #ML #Generative
Imagine This! Scripts to Compositions to Videos: #ML #Generative
#Prediction: The combination Machine Learning and Human Mindfulness will be a major industry by 2023. #ML #Mindful
Synthesizing Programs for Images using Reinforced Adversarial Learning:
Paper: https://arxiv.org/abs/1804.01118v1
Video: https://www.youtube.com/watch?v=iSyvwAwa7vk
Deep Image Prior:
Paper: https://arxiv.org/abs/1711.10925v3
Project: https://dmitryulyanov.github.io/deep_image_prior
Code: https://github.com/DmitryUlyanov/deep-image-prior
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images:
Paper: https://arxiv.org/abs/1804.01654v1
Project: http://bigvid.fudan.edu.cn/pixel2mesh/
SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval:
Paper: https://arxiv.org/abs/1804.01401v1
Dataset: http://sketchx.eecs.qmul.ac.uk/downloads/
A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation:
Paper: https://arxiv.org/abs/1804.00522v2
Demo: https://einstein.ai/research/a-multi-discriminator-cyclegan-for-unsupervised-non-parallel-speech-domain-adaptation
"How Machine Learning Boosts Your Digital Creativity" - by @AdobeSensei:
https://theblog.adobe.com/machine-learning-boosts-digital-creativity/ #ML #Creativity
Fauxtomation - "When workers get rendered invisible to maintain illusion machines & systems smarter than they actually are" (coined by @astradisastra).
Leading AI researchers threaten Korean university with boycott over its work on ‘killer robots’: https://www.theverge.com/2018/4/4/17196818/ai-boycot-killer-robots-kaist-university-hanwha and https://www.theguardian.com/technology/2018/apr/05/killer-robots-south-korea-university-boycott-artifical-intelligence-hanwha #ML #Robot #Ethics #Military
"Artificial Intelligence will take over all art production in the world" - A illustration by Mattias Adolfsson: https://ello.co/mattiasadolfsson/post/llshv5_2oria_e0uifrm_q #ML #Art
Musical Composition with Stochastic Context-Free Grammars: #ML #Generative #Music
https://pdfs.semanticscholar.org/ae9a/f878d3b91e2e154adf571182fa1e99aa0199.pdf
A Probabilistic Context-Free Grammar for Melodic Reduction:
https://pdfs.semanticscholar.org/5f33/c5a759e163b511d52b72c2b25ed48243f2fd.pdf
Modeling Musical Structure with Parametric Grammars:
http://www.grappa.univ-lille3.fr/~staworko/papers/staworko-mcm15.pdf
Probabilistic Grammars for Music:
http://www.inf.ed.ac.uk/teaching/courses/mi/prac2/prob_grammars.pdf
cfml: the context-free music language:
https://eis-blog.soe.ucsc.edu/2009/11/cfml-the-context-free-music-language/
Music Generation and Algorithmic Composition:
https://www.cs.cmu.edu/~music/cmsip/slides/05-algo-comp.pdf
Grammar Based Music Composition:
http://users.monash.edu/~jonmc/research/Papers/L-systemsMusic.pdf
The combination Machine Learning and Human Mindfulness will be a major industry by 2023.
Convolutional Sketch Inversion: #ML #Generative
Paper: https://arxiv.org/abs/1606.03073
Code: https://github.com/TengdaHan/Convolutional_Sketch_Inversion
Image Generation from Scene Graphs: https://arxiv.org/abs/1804.01622 #ML #Generative
DeSIGN: Design Inspiration from Generative Networks:
https://arxiv.org/abs/1804.00921v1
FLIPDIAL: A Generative Model for Two-Way Visual Dialogue:
https://arxiv.org/abs/1802.03803v2
Training VAEs Under Structured Residuals:
https://arxiv.org/abs/1804.01050v1
Seeing Voices and Hearing Faces: Cross-modal biometric matching:
https://arxiv.org/abs/1804.00326v2
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks:
https://arxiv.org/abs/1711.07064v4
Deep Texture Manifold for Ground Terrain Recognition:
https://arxiv.org/abs/1803.10896v2
"Google Workers Urge C.E.O. To Pull Out of Pentagon A.I. Project": #ML #Politics #Military
https://www.nytimes.com/2018/04/04/technology/google-letter-ceo-pentagon-project.html
What will our society look like when artificial intelligence is everywhere? - by Stephan Talty:
https://www.smithsonianmag.com/innovation/artificial-intelligence-future-scenarios-180968403/ #ML
Stroke Controllable Fast Style Transfer: http://yongchengjing.com/StrokeControllable
Paper: https://arxiv.org/abs/1802.07101
Code: https://github.com/LouieYang/stroke-controllable-fast-style-transfer #ML #Generative
Expressive Speech Synthesis with Tacotron: #ML #Music
https://research.googleblog.com/2018/03/expressive-speech-synthesis-with.html
Tensorflow Implementation of Expressive Tacotron:
https://github.com/Kyubyong/expressive_tacotron
Machine Learning in JavaScript - a presentation by Nikhil Thorat and Daniel Smilkov: #ML
Procedural Worlds from Simple Tiles: #ML #Generative
http://ijdykeman.github.io/ml/2017/10/12/wang-tile-procedural-generation.html
The 3 stages of Creative AI: #ML #Creativity #Ideas
1. Discovery: "Wow, ML can generate creative stuff, crazy!"
2. Reality: "Oh, tech and creativity are hard! ML is not magic after all."
3. Wisdom: "How" to generate is interesting - but deciding "What" to generate "Why" is the art of life.
Reusing Neural Speech Representations for Auditory Emotion Recognition:
https://arxiv.org/abs/1803.11508 #ML #Emotion