AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Hendrycks et al.: https://arxiv.org/abs/1912.02781
#ArtificialIntelligence #DeepLearning #MachineLearning
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
Raia Hadsell - Deep Reinforcement Learning & Real World Challenges - YouTube
YouTube
Raia Hadsell - Deep Reinforcement Learning & Real World Challenges
Raia Hadsell is a research scientist on the Deep Learning team at DeepMind. She moved to London to join DeepMind in early 2014, feeling that her fundamental research interests in robotics, neural networks, and real world learning systems were well-aligned…
Generate realistic and diverse images using this state of the art model released recently (StarGAN v2)!
https://www.profillic.com/paper/arxiv:1912.01865
https://www.profillic.com/paper/arxiv:1912.01865
Profillic
StarGAN v2: Diverse Image Synthesis for Multiple Domains - Profillic
Explore state-of-the-art in machine learning, AI, and robotics. Browse models, source code, papers by topics and authors. Connect with researchers and engineers working on related problems in machine learning, deep learning, natural language processing, robotics…
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke et al.: https://arxiv.org/abs/1912.01703
#ArtificialIntelligence #deepLearning #PyTorch
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
"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
YouTube
"Deep Learning was great, what's next?" - Yoshua Bengio (2/4)
Interested in attending a RE•WORK Summit? Get 25% off your pass from December 2-6! See the list of summits here - https://bit.ly/2DrrCbj "Deep Learning was g...
PhiFlow
Research-oriented differentiable fluid simulation framework : https://github.com/tum-pbs/PhiFlow
#ArtificialIntelligence #MachineLearning #TensorFlow
Research-oriented differentiable fluid simulation framework : https://github.com/tum-pbs/PhiFlow
#ArtificialIntelligence #MachineLearning #TensorFlow
GitHub
GitHub - tum-pbs/PhiFlow: A differentiable PDE solving framework for machine learning
A differentiable PDE solving framework for machine learning - tum-pbs/PhiFlow
Understanding Transfer Learning for Medical Imaging
https://ai.googleblog.com/2019/12/understanding-transfer-learning-for.html
https://ai.googleblog.com/2019/12/understanding-transfer-learning-for.html
blog.research.google
Understanding Transfer Learning for Medical Imaging
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)
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
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
Alexia Jolicoeur-Martineau
Connections between SVMs, Wasserstein distance and GANs
Check out my new paper entitled “Support Vector Machines, Wasserstein’s distance and gradient-penalty GANs are connected”! 😸 In this paper, we explain how one can derive SVMs and …
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
Kuznetsov et al.: https://arxiv.org/abs/1910.13148
#MachineLearning #NeurIPS #NeurIPS2019
arXiv.org
A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for...
Generative models produce realistic objects in many domains, including text, image, video, and audio synthesis. Most popular models---Generative Adversarial Networks (GANs) and Variational...
BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search
White et al.: https://arxiv.org/abs/1910.11858
#Bayesian #Optimization #NeuralArchitectureSearch
White et al.: https://arxiv.org/abs/1910.11858
#Bayesian #Optimization #NeuralArchitectureSearch
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
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
ML Tenure-Track Faculty position at University of Montreal & Mila
The Department of Computer Science and Operations Research of University of Montreal is seeking applications for a full-time tenure-track faculty position (at assistant or associate professor level), in areas related to machine learning and its applications in connected fields (e.g., healthcare, natural language processing, computer vision, robotics). This position comes with membership to Mila, one of the largest academic research group in deep learning worldwide and combining the strengths of University of Montreal, McGill University, HEC and Polytechnique in a common beautfiul location, with nearby access to many industrial research labs like FAIR, Microsoft Research, Element AI or Borealis AI.
See more information and how to apply on the Mila page :
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/
Feel free to email me for informal inquiries (use "MLJOB:" in your subject line) or approach me during the NeurIPS conference next week (many Mila professors will be there -- see https://mila.quebec/en/mila/team/ ).
Best,
Simon
===
Some additional notes:
* Deadline is January 6th, 2019.
* The selected candidates could be eligible for a Canadian CIFAR
AI (CCAI) Chair. More information about the program here:
https://www.cifar.ca/ai/pan-canadian-artificial-intelligence-strategy
* Montreal is home to a very active ML community, including university-led institutes such as Mila that received considerable federal funding, industry-led ML research groups (Google, Facebook, Microsoft, Samsung, Borealis, and several more), as well as a thriving ML startup community. Montreal is a historic and cosmopolitan city, home to no less than six universities, and considered one of the best cities for students. It was recently ranked by InterNations as the top city in North America for expats: https://www.internations.org/press/press-release/the-best-and-worst-cities-in-the-world-to-live-and-work-abroad-in-2020-39934 .
* In the last hiring season, we are happy to announce that UdeM has hired Aishwarya Agrawal (https://www.cc.gatech.edu/~aagrawal307/), Irina Rish ( https://sites.google.com/site/irinarish/ ) and Pierre-Luc Bacon ( https://pierrelucbacon.com/ ).
The Department of Computer Science and Operations Research of University of Montreal is seeking applications for a full-time tenure-track faculty position (at assistant or associate professor level), in areas related to machine learning and its applications in connected fields (e.g., healthcare, natural language processing, computer vision, robotics). This position comes with membership to Mila, one of the largest academic research group in deep learning worldwide and combining the strengths of University of Montreal, McGill University, HEC and Polytechnique in a common beautfiul location, with nearby access to many industrial research labs like FAIR, Microsoft Research, Element AI or Borealis AI.
See more information and how to apply on the Mila page :
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/
Feel free to email me for informal inquiries (use "MLJOB:" in your subject line) or approach me during the NeurIPS conference next week (many Mila professors will be there -- see https://mila.quebec/en/mila/team/ ).
Best,
Simon
===
Some additional notes:
* Deadline is January 6th, 2019.
* The selected candidates could be eligible for a Canadian CIFAR
AI (CCAI) Chair. More information about the program here:
https://www.cifar.ca/ai/pan-canadian-artificial-intelligence-strategy
* Montreal is home to a very active ML community, including university-led institutes such as Mila that received considerable federal funding, industry-led ML research groups (Google, Facebook, Microsoft, Samsung, Borealis, and several more), as well as a thriving ML startup community. Montreal is a historic and cosmopolitan city, home to no less than six universities, and considered one of the best cities for students. It was recently ranked by InterNations as the top city in North America for expats: https://www.internations.org/press/press-release/the-best-and-worst-cities-in-the-world-to-live-and-work-abroad-in-2020-39934 .
* In the last hiring season, we are happy to announce that UdeM has hired Aishwarya Agrawal (https://www.cc.gatech.edu/~aagrawal307/), Irina Rish ( https://sites.google.com/site/irinarish/ ) and Pierre-Luc Bacon ( https://pierrelucbacon.com/ ).
Deep Learning for Symbolic Mathematics
https://arxiv.org/abs/1912.01412v1
https://arxiv.org/abs/1912.01412v1
ArtificialIntelligenceArticles
Deep Learning for Symbolic Mathematics https://arxiv.org/abs/1912.01412v1
Deep Learning for Symbolic Mathematics
Authors show that ANN can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations.
#neuralnetworks #deeplearning #mathematics #math #matlab
https://arxiv.org/abs/1912.01412
Authors show that ANN can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations.
#neuralnetworks #deeplearning #mathematics #math #matlab
https://arxiv.org/abs/1912.01412
Dream to Control: Learning Behaviors by Latent Imagination
https://arxiv.org/abs/1912.01603v1
https://arxiv.org/abs/1912.01603v1
When Does Label Smoothing Help? by Geoffrey Hinton , Rafael Müller, Simon Kornblith, https://arxiv.org/abs/1906.02629
arXiv.org
When Does Label Smoothing Help?
The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform...
Deep learning in The Brain : https://goo.gl/oqUXqV @ArtificialIntelligenceArticles