GQN — Generative Query Network
The agent infers the image from a viewpoint based on the pre-knowledge of the environment and viewpoints
Comprised of three architectures:
The representation architecture takes images from different viewpoints to yield a concise abstract scene representation.
The generation architecture generates an image for a new query viewpoint.
The inference architecture served as the encoder in a variational autoencoder provides a way to train the other two architectures in an unsupervised manner.
Blogs
Very intuitive explanation:
https://xlnwel.github.io/blog/representation%20learning/GQN/
DeepMind: https://deepmind.com/blog/article/neural-scene-representation-and-rendering

Artificial Intelligence: Reality vs Hype

Landing AI Founder and CEO Andrew Ng sits down with Bloomberg’s Austin Carr at Sooner Than You Think in Brooklyn. (Source: Bloomberg)

https://www.bloomberg.com/news/videos/2019-10-30/artificial-intelligence-reality-vs-hype-video

BPE-Dropout: Simple and Effective Subword Regularization
https://arxiv.org/abs/1910.13267

A New Spin on the Quantum Brain
https://www.quantamagazine.org/a-new-spin-on-the-quantum-brain-20161102/

Keras / TPU integration in Tensorflow 2.1 (unreleased)
Google Cloud Platform : https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/courses/fast-and-lean-data-science/README-TF2.1.md
#Keras #TPU #Tensorflow https://t.iss.one/ArtificialIntelligenceArticles

Learning Data Manipulation for Augmentation and Weighting

Zhiting Hu, Bowen Tan, Ruslan Salakhutdinov, Tom Mitchell, Eric P. Xing : https://arxiv.org/abs/1910.12795

#ArtificialIntelligence #MachineLearning #ReinforcementLearning

Neural Density Estimation and Likelihood-free Inference
George Papamakarios : https://arxiv.org/pdf/1910.13233.pdf
#Bayesian #NeuralDensityEstimation #Inference

Introduction to Capsules by Sara Sabour, Google


https://www.youtube.com/watch?v=zRg3IuxaJ6I

https://t.iss.one/ArtificialIntelligenceArticles

Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber : https://arxiv.org/abs/1910.04098
#ArtificialIntelligence #MetaReinforcementLearning #ReinforcementLearning

Engineers at Google have unveiled Dex, a prototype functional language designed for array processing. Array processing is a cornerstone of the math used in machine learning applications and other computationally intensive work.

#dex #machinelearning #linearalgebra

https://openreview.net/pdf?id=rJxd7vsWPS

Artificial Intelligence replaces Fashion photographers as it renders photo-realistic images of fashion models wearing outfits from input images of isolated clothing items.

Takes #StyleGAN to the next level.
Great work by zalandoresearch #iccv2019

Read https://arxiv.org/pdf/1908.08847.pdf

interesting.
https://www.biorxiv.org/content/10.1101/787101v2 https://www.youtube.com/watch?time_continue=40&v=nf-P3b2AnZw&fbclid=IwAR3Vtk9MKYPb6KFRIvk3Bgjeedw-i-8th1srJpbNQVHR_KpOzMa-p50RHx0

Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber : https://arxiv.org/abs/1910.04098
#ArtificialIntelligence #MetaReinforcementLearning #ReinforcementLearning

NIPS 2017 Invited talk
"Deep Reinforcement Learning with Subgoals"
By David Silver: https://vimeo.com/249557775
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #ReinforcementLearning

PyRoboLearn: A Python Framework for Robot Learning Practitioners

Delhaisse et al.: https://robotlearn.github.io/pyrobolearn/

#ArtificialIntelligence #Python #Robotics

Google PhD Fellowship program is now accepting applications.
Deadline is Dec 1st.

Google PhD Fellowships directly support graduate students as they pursue their PhD, as well as connect them to a Google Research Mentor.


https://ai.google/research/outreach/phd-fellowship/