Fast Task Inference with Variational Intrinsic Successor Features
A novel algorithm that learns controllable features that can be leveraged to provide enhanced generalization and fast task inference through the successor feature framework.
The fundamental problem they face is a need to generalize between different latent codes, a task to which neural networks alone seem poorly suited.
To solve this generalization and slow inference problem by making use of successor features
To show that variational-intrinsic-control/diversity-is-all-you-need algorithms can be adapted to learn precisely the features needed by successor features
PAPER
https://arxiv.org/pdf/1906.05030.pdf

Probing the State of the Art: A Critical Look at Visual Representation Evaluation
Resnick et al.: https://arxiv.org/abs/1912.00215
#ArtificialIntelligence #DeepLearning #MachineLearning

STANFORD CENTER FOR PROFESSIONAL DEVELOPMENT AI RESOURCE HUB
https://onlinehub.stanford.edu/

Latest from Google brain researchers: The intelligent (reinforcement learning) agent learns a world model from past experience and efficiently learns farsighted behaviors

https://www.profillic.com/paper/arxiv:1912.01603

You have a paper accepted at #NeurIPS but will not be in Vancouver? Consider presenting your work at a local meetup →

https://www.google.com/maps/d/u/0/viewer?mid=1ezbjW7AGg_9APIshVTu09uhJbXkMO5SI&ll=17.28121049467974%2C13.983942200000001&z=-1&fbclid=IwAR2nvS6YA1SnvCetrI8noxOH5ZSPLjwydMxS2vbhlqd9OBQCpFY1krS5t0A

We are recruiting new professors at Mila, again. Strong likelihood of obtaining a CIFAR AI Chair (with salary supplement and teaching reduction). This position is in my department at U. Montreal.
https://mila.quebec/en/2019/12/assistant-professor-in-machine-learning-faculte-des-arts-et-des-sciences-department-of-computer-science-and-operations-research-universite-de-montreal/?fbclid=IwAR3G5zZRNFqKnUVs9jVswJUH8qZWj2DQrpsnk4gmrlkvuA7ZkwDq6eLxGWE

Stacked Capsule Autoencoders
Kosiorek et al.: https://arxiv.org/abs/1906.06818
#ArtificialIntelligence #Capsule #Autoencoders

Deep Learning for Symbolic Mathematics
Guillaume Lample, François Charton : https://arxiv.org/abs/1912.01412
#ArtificialIntelligence #DeepLearning #SymbolicAI

Stacked Capsule Autoencoders by Geoffrey E． Hinton
Adam R． Kosiorek, Sara Sabour, Yee Whye Teh,
https://arxiv.org/abs/1906.06818 https://t.iss.one/ArtificialIntelligenceArticles

How To Build Your Own MuZero AI Using Python (Part 1/3)
Blog by David Foster : https://medium.com/applied-data-science/how-to-build-your-own-muzero-in-python-f77d5718061a
#MachineLearning #DeepLearning #DataScience #ArtificialIntelligence #AI

GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors
Masato Hagiwara, Masato Mita : https://arxiv.org/abs/1911.12893
Code & Dataset https://github.com/mhagiwara/github-typo-corpus
#ArtificialIntelligence #DeepLearning #NLP

Buffalo University Comprehensive Lecture Slides for Machine Learning and Deep Learning

By Professor Sargur Srihari

Machine Learning:
https://cedar.buffalo.edu/~srihari/CSE574/

Deep Learning:
https://cedar.buffalo.edu/~srihari/CSE676/index.html

Probabilistic Graphical Models:
https://cedar.buffalo.edu/~srihari/CSE674/

Data Mining:
https://cedar.buffalo.edu/~srihari/CSE626/index.html

#machinelearning #deeplearning #datamining #AI #artificialintelligence

Mathematicians and neuroscientists have created the first anatomically accurate model that explains how vision is possible.
join

@ArtificialIntelligenceArticles
https://www.quantamagazine.org/a-mathematical-model-unlocks-the-secrets-of-vision-20190821/

SSL FTW!
Pretext-Invariant Representation Learning: a self-supervised method based on Siamese nets for visual feature learning from FAIR.
Beats supervised pre-training & all previous SSL methods on ImageNet, VOC-07-12, etc. https://arxiv.org/abs/1912.01991

Major trends in #NLP : a review of 20 years of #ACL research

The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) is starting this week in Florence, Italy. We took the opportunity to review major research trends in the animated NLP space and formulate some implications from the business perspective. The article is backed by a statistical and — guess what — NLP-based analysis of ACL papers from the last 20 years

https://towardsdatascience.com/major-trends-in-nlp-a-review-of-20-years-of-acl-research-56f5520d473

RGPNet: A Real-Time General Purpose Semantic Segmentation
Elahe Arani, Shabbir Marzban, Andrei Pata, Bahram Zonooz : https://arxiv.org/abs/1912.01394
#ArtificialIntelligence #DeepLearning #MachineLearning

Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
Greg Yang : https://arxiv.org/abs/1910.12478
#ArtificialIntelligence #DeepLearning #NeurIPS2019

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Hendrycks et al.: https://arxiv.org/abs/1912.02781
#ArtificialIntelligence #DeepLearning #MachineLearning

https://www.youtube.com/watch?v=mckulxKWyoc
Raia Hadsell - Deep Reinforcement Learning & Real World Challenges - YouTube

Generate realistic and diverse images using this state of the art model released recently (StarGAN v2)!

https://www.profillic.com/paper/arxiv:1912.01865