'The Deep Learning Revolution' - Geoffrey Hinton - RSE President's Lecture 2019
https://www.youtube.com/watch?v=re-SRA5UZQw&feature=youtu.be
https://t.iss.one/ArtificialIntelligenceArticles
https://www.youtube.com/watch?v=re-SRA5UZQw&feature=youtu.be
https://t.iss.one/ArtificialIntelligenceArticles
YouTube
'The Deep Learning Revolution' - Geoffrey Hinton - RSE President's Lecture 2019
"There have been two very different paradigms for Artificial Intelligence: the logic-inspired paradigm focused on reasoning and language, and assumed that the core of intelligence was manipulation of symbolic expressions; the biologically-inspired paradigm…
BEST PAPER AWARDS at #AC L2019
https://www.acl2019.org/EN/nominations-for-acl-2019-best-paper-awards.xhtml
https://www.acl2019.org/EN/nominations-for-acl-2019-best-paper-awards.xhtml
PhD position at the Donders: machine learning, sleep enhancement, lucid dreaming.
dreslerlab.org/arenar
Also, if you have a strong MEG/EEG/BCI background, please inquire for positions.
dreslerlab.org/arenar
Also, if you have a strong MEG/EEG/BCI background, please inquire for positions.
Donders Sleep & Memory Lab | Martin Dresler
PhD position: Machine learning to record and enhance sleep and lucid dreaming
Arenar B.V. and the Donders Institute offer a joint PhD position combining data science/AI and wearable EEG technology with sleep/dream research. In this project, the wearable sleep EEG headband iB…
MIT 6.S191: Recurrent Neural Networks
https://www.youtube.com/watch?v=_h66BW-xNgk
https://www.youtube.com/watch?v=_h66BW-xNgk
YouTube
MIT 6.S191 (2019): Recurrent Neural Networks
MIT Introduction to Deep Learning 6.S191: Lecture 2
Deep Sequence Modeling with Recurrent Neural Networks
Lecturer: Ava Soleimany
January 2019
For all lectures, slides and lab materials: https://introtodeeplearning.com
Deep Sequence Modeling with Recurrent Neural Networks
Lecturer: Ava Soleimany
January 2019
For all lectures, slides and lab materials: https://introtodeeplearning.com
10 Exciting Ideas of 2018 in NLP
https://ruder.io/10-exciting-ideas-of-2018-in-nlp/
https://ruder.io/10-exciting-ideas-of-2018-in-nlp/
Great applications for mobile robotics!
Real-time Vision-based Depth Reconstruction
https://www.profillic.com/paper/arxiv:1907.07210
They experiment with several FCNN architectures and introduce a few enhancements aimed at increasing both the effectiveness and the efficiency of the inference.
Real-time Vision-based Depth Reconstruction
https://www.profillic.com/paper/arxiv:1907.07210
They experiment with several FCNN architectures and introduce a few enhancements aimed at increasing both the effectiveness and the efficiency of the inference.
Profillic
Profillic: AI research & source code to supercharge your projects
Explore state-of-the-art in machine learning, AI, and robotics research. Browse papers, source code, models, and more by topics and authors. Connect with researchers and engineers working on related problems in machine learning, deep learning, natural language…
Speech2Face: Learning the Face Behind a Voice
Oh et al.: https://arxiv.org/abs/1905.09773
#ArtificialIntelligence #MachineLearning #Multimedia
Oh et al.: https://arxiv.org/abs/1905.09773
#ArtificialIntelligence #MachineLearning #Multimedia
arXiv.org
Speech2Face: Learning the Face Behind a Voice
How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person...
Optuna: A Next-generation Hyperparameter Optimization Framework
Akiba et al.: https://arxiv.org/abs/1907.10902
#ArtificialIntelligence #DataScience #MachineLearning
Akiba et al.: https://arxiv.org/abs/1907.10902
#ArtificialIntelligence #DataScience #MachineLearning
arXiv.org
Optuna: A Next-generation Hyperparameter Optimization Framework
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to...
It’s hard to think of a better place than #Vancouver for #CVPR 2023. Announcing our bid -- a strong organizing team at a beautiful convention centre in a great city.
Greg Mori, Fei-Fei Li, Michael Brown, Yoichi Sato as General Chairs; Vladlen Koltun, Svetlana Lazebnik, Ross Girshick, Andreas Geiger as Program Chairs; Olga Russakovsky and Serena Yeung as Workshop Chairs, Jianxin Wu and Siyu Tang as Tutorial Chairs, Kwang Moo Yi and Leonid Sigal as Local Arrangements Chairs, Catherine Qi Zhao as Doctoral Consortium Chair, Gim Hee Lee and Jon Barron as Demo Chairs.
Check out the full bid document:
www2.cs.sfu.ca/~mori/cvpr2023_vancouver.pdf
Greg Mori, Fei-Fei Li, Michael Brown, Yoichi Sato as General Chairs; Vladlen Koltun, Svetlana Lazebnik, Ross Girshick, Andreas Geiger as Program Chairs; Olga Russakovsky and Serena Yeung as Workshop Chairs, Jianxin Wu and Siyu Tang as Tutorial Chairs, Kwang Moo Yi and Leonid Sigal as Local Arrangements Chairs, Catherine Qi Zhao as Doctoral Consortium Chair, Gim Hee Lee and Jon Barron as Demo Chairs.
Check out the full bid document:
www2.cs.sfu.ca/~mori/cvpr2023_vancouver.pdf
Go-Explore: a New Approach for Hard-Exploration Problems
Ecoffet et al.: https://arxiv.org/abs/1901.10995
#MachineLearning #ArtificialIntelligence
Ecoffet et al.: https://arxiv.org/abs/1901.10995
#MachineLearning #ArtificialIntelligence
arXiv.org
Go-Explore: a New Approach for Hard-Exploration Problems
A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains:...
"The Bitter Lesson"
The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin.
In computer chess, the methods that defeated the world champion, Kasparov, in 1997, were based on massive, deep search (…) A similar pattern of research progress was seen in computer Go, only delayed by a further 20 years.
One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with increased computation, even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are search and learning.
Rich Sutton, March 13, 2019: https://www.incompleteideas.net/IncIdeas/BitterLesson.html
#Learning #ReinforcementLearning #Search
The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin.
In computer chess, the methods that defeated the world champion, Kasparov, in 1997, were based on massive, deep search (…) A similar pattern of research progress was seen in computer Go, only delayed by a further 20 years.
One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with increased computation, even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are search and learning.
Rich Sutton, March 13, 2019: https://www.incompleteideas.net/IncIdeas/BitterLesson.html
#Learning #ReinforcementLearning #Search
"Subspace Neural Physics: Fast Data-Driven Interactive Simulation"
Holden et al.: https://theorangeduck.com/media/uploads/other_stuff/deep-cloth-paper.pdf
#machinelearning #neuralnetworks #physics
Holden et al.: https://theorangeduck.com/media/uploads/other_stuff/deep-cloth-paper.pdf
#machinelearning #neuralnetworks #physics
Optuna: A Next-generation Hyperparameter Optimization Framework
Akiba et al.: https://arxiv.org/abs/1907.10902
#ArtificialIntelligence #DataScience #MachineLearning
Akiba et al.: https://arxiv.org/abs/1907.10902
#ArtificialIntelligence #DataScience #MachineLearning
arXiv.org
Optuna: A Next-generation Hyperparameter Optimization Framework
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to...
Y-Autoencoders: disentangling latent representations via sequential-encoding
Article: https://arxiv.org/abs/1907.10949
GitHub: https://github.com/mpatacchiola/Y-AE
Article: https://arxiv.org/abs/1907.10949
GitHub: https://github.com/mpatacchiola/Y-AE
arXiv.org
Y-Autoencoders: disentangling latent representations via...
In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs)....
“AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence”
This paper describes an exciting path that ultimately may be successful at producing general AI. It is based on the clear trend in machine learning that hand-designed solutions eventually are replaced by more effective, learned solutions.
The idea is to create an AI-generating algorithm (AI-GA), which automatically learns how to produce general AI. Three Pillars are essential for the approach: (1) meta-learning architectures, (2) meta-learning the learning algorithms themselves, and (3) generating effective learning environments.
Jeff Clune: https://arxiv.org/abs/1905.10985
#AGI #AGIFirst #ArtificialGeneralIntelligence
This paper describes an exciting path that ultimately may be successful at producing general AI. It is based on the clear trend in machine learning that hand-designed solutions eventually are replaced by more effective, learned solutions.
The idea is to create an AI-generating algorithm (AI-GA), which automatically learns how to produce general AI. Three Pillars are essential for the approach: (1) meta-learning architectures, (2) meta-learning the learning algorithms themselves, and (3) generating effective learning environments.
Jeff Clune: https://arxiv.org/abs/1905.10985
#AGI #AGIFirst #ArtificialGeneralIntelligence
TAMGU: A new open source programming language to help create, annotate and augment corpora and data. - Naver Labs Europe
https://europe.naverlabs.com/blog/tamgu/
https://europe.naverlabs.com/blog/tamgu/
Naverlabs
TAMGU: A new open source programming language to help create, annotate and augment corpora and data. - Naver Labs Europe
Tamgu has been designed to make cleaning or creating corpora as simple as possible. Go try it out!
A "worrying analysis":
"18 [#deeplearning] algorithms ... presented at top-level research conferences ... Only 7 of them could be reproduced w/ reasonable effort ... 6 of them can often be outperformed w/ comparably simple heuristic methods."
https://arxiv.org/abs/1907.06902v1
"18 [#deeplearning] algorithms ... presented at top-level research conferences ... Only 7 of them could be reproduced w/ reasonable effort ... 6 of them can often be outperformed w/ comparably simple heuristic methods."
https://arxiv.org/abs/1907.06902v1
One-stage Shape Instantiation from a Single 2D Image to 3D Point Cloud. arxiv.org/abs/1907.10763
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference. arxiv.org/abs/1907.10739