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

PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke et al.: https://arxiv.org/abs/1912.01703
#ArtificialIntelligence #deepLearning #PyTorch

Pre-Debate Material
"Deep Learning was great, what's next?"
What is missing to extend Deep Learning to reach human-level AI? Yoshua Bengio : https://youtu.be/cBt5EvHRS5M?t=70
RSVP (2320 people already signed up) at https://bengio-marcus.eventbrite.ca
#AIDebate #ArtificialIntelligence #DeepLearning

PhiFlow
Research-oriented differentiable fluid simulation framework : https://github.com/tum-pbs/PhiFlow
#ArtificialIntelligence #MachineLearning #TensorFlow

Understanding Transfer Learning for Medical Imaging
https://ai.googleblog.com/2019/12/understanding-transfer-learning-for.html

Capsule Routing via Variational Bayes (AAAI 2020)

Hi guys, check out our new paper on Capsule networks to appear in AAAI 2020.

[https://arxiv.org/pdf/1905.11455.pdf](https://arxiv.org/pdf/1905.11455.pdf)

Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs
Alexia Jolicoeur-Martineau and Ioannis Mitliagkas : https://arxiv.org/abs/1910.06922
Blog : https://ajolicoeur.wordpress.com/MaximumMarginGAN
Code : https://github.com/AlexiaJM/MaximumMarginGANs
#SupportVectorMachines #GANs #ArtificialIntelligence

A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models
Kuznetsov et al.: https://arxiv.org/abs/1910.13148
#MachineLearning #NeurIPS #NeurIPS2019

BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search
White et al.: https://arxiv.org/abs/1910.11858
#Bayesian #Optimization #NeuralArchitectureSearch

https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2058576/?

Research Fellow / Senior Research Fellow at the intersection of machine learning and robotics
We are looking for a Research Fellow / Senior Research Fellow at the intersection of robotics and machine learning.

We are looking for a (Senior) Research Fellow at the intersection of robotics and machine learning.

Autonomous robots will play an increasingly important role in the future, e.g., in the context of healthcare, space exploration, or supporting humans in day-to-day activities. Key challenges, autonomous robots face are that they need to be able to learn from data and adapt fast to new situations without strong human interventions. Currently, autonomous learning systems either require vast amounts of data or they require human guidance. This project centers around approaches for data-efficient autonomous learning for robotics, e.g., by means of probabilistic modeling, transfer learning or using generic priors that constrain the learning system.

You will be part of the Statistical Machine Learning Group, which is located at UCL's Centre for Artificial Intelligence. We have a strong background in probabilistic modeling, data-efficient machine learning, and reinforcement learning. The successful applicant will lead and contribute to research projects at the intersection of statistical machine learning and climate science. They are also expected to contribute to student supervision and interact with research and project partners. The key objective is to design and evaluate machine learning approaches to advance the current state of the art in robot learning.

The post is graded as Grade 7 or Grade 8, with starting salary in the range £35,965 to £43,470 (Grade 7) or £44,674 to £52,701 (Grade 8) per annum (including London Allowance). Progression through the salary scale is incremental.

The funding for this post is for 24 months in the first instance.

The successful applicant will have a PhD (or close to be obtaining a PhD) in machine learning, statistics, computer science, robotics or a relevant area. They should have a track record of internationally recognized research and be able to work as part of a team. Research skills (theoretical and empirical, planning and documentary) plus effective written and verbal communication skills are essential.

More details and a link to the application can be found at
https://atsv7.wcn.co.uk/search_engine/jobs.cgi?SID=amNvZGU9MTg0MDg1MSZ2dF90ZW1wbGF0ZT05NjYmb3duZXI9NTA0MTE3OCZvd25lcnR5cGU9ZmFpciZicmFuZF9pZD0wJnZhY3R5cGU9MTI3NiZwb3N0aW5nX2NvZGU9MjI0

Please contact me if you have questions: [email protected]

I will also be at NeurIPS this month, and I'm happy to discuss opportunities in perso