AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
Jeff Clune: https://arxiv.org/abs/1905.10985
#ArtificialIntelligence #ArtificialGeneralIntelligence #AGI
Jeff Clune: https://arxiv.org/abs/1905.10985
#ArtificialIntelligence #ArtificialGeneralIntelligence #AGI
arXiv.org
AI-GAs: AI-generating algorithms, an alternate paradigm for...
Perhaps the most ambitious scientific quest in human history is the creation of general artificial intelligence, which roughly means AI that is as smart or smarter than humans. The dominant...
Understanding Hinton’s Capsule Networks. Part I: Intuition.
Blog by Max Pechyonkin: https://medium.com/ai³-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b
#MachineLearning #DeepLearning #GeoffreyHinton #ArtificialIntelligence #Theory
Blog by Max Pechyonkin: https://medium.com/ai³-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b
#MachineLearning #DeepLearning #GeoffreyHinton #ArtificialIntelligence #Theory
Medium
Understanding Hinton’s Capsule Networks. Part I: Intuition.
Part of Understanding Hinton’s Capsule Networks Series:
"End-to-End Deep Reinforcement Learning without Reward Engineering"
They developed an end-to-end method that allows robots to learn from a modest number of images that depict successful completion of a task.
https://bair.berkeley.edu/blog/2019/05/28/end-to-end/
They developed an end-to-end method that allows robots to learn from a modest number of images that depict successful completion of a task.
https://bair.berkeley.edu/blog/2019/05/28/end-to-end/
The Berkeley Artificial Intelligence Research Blog
End-to-End Deep Reinforcement Learning
without Reward Engineering
without Reward Engineering
The BAIR Blog
"Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor"
Do word embeddings really say that man is to doctor as woman is to nurse? Apparently not!
Nissim et al.: https://arxiv.org/abs/1905.09866
#ArtificialIntelligence #MachineLearning #NLProc #bias
Do word embeddings really say that man is to doctor as woman is to nurse? Apparently not!
Nissim et al.: https://arxiv.org/abs/1905.09866
#ArtificialIntelligence #MachineLearning #NLProc #bias
arXiv.org
Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor
Analogies such as "man is to king as woman is to X" are often used to illustrate the amazing power of word embeddings. Concurrently, they have also been used to expose how strongly human biases...
How to deliver on Machine Learning projects
A guide to the ML Engineering Loop.
By Emmanuel Ameisen and Adam Coates: https://blog.insightdatascience.com/how-to-deliver-on-machine-learning-projects-c8d82ce642b0
#ArtificialIntelligence #BigData #DataScience #DeepLearning #MachineLearning
A guide to the ML Engineering Loop.
By Emmanuel Ameisen and Adam Coates: https://blog.insightdatascience.com/how-to-deliver-on-machine-learning-projects-c8d82ce642b0
#ArtificialIntelligence #BigData #DataScience #DeepLearning #MachineLearning
Medium
How to deliver on Machine Learning projects
A guide to the ML Engineering Loop
Open-ended learning in symmetric zero-sum games
Balduzzi et al.: https://proceedings.mlr.press/v97/balduzzi19a.html
#ArtificialIntelligence #MachineLearning #Nash #GameTheory
Balduzzi et al.: https://proceedings.mlr.press/v97/balduzzi19a.html
#ArtificialIntelligence #MachineLearning #Nash #GameTheory
PMLR
Open-ended learning in symmetric zero-sum games
Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them ‘winner’ and ‘loser’. If the game ...
Utterance-level Aggregation for Speaker Recognition in the Wild
Project page https://www.robots.ox.ac.uk/~vgg/research/speakerID/
paper https://arxiv.org/pdf/1902.10107.pdf
Project page https://www.robots.ox.ac.uk/~vgg/research/speakerID/
paper https://arxiv.org/pdf/1902.10107.pdf
www.robots.ox.ac.uk
Utterance-level Aggregation for Speaker Recognition in the Wild
Weidi Xie, Arsha Nagrani, Joon Son Chung, Andrew Zisserman,
Convex Optimization: Algorithms and Complexity
Sébastien Bubeck
Theory Group, Microsoft Research
[email protected]
https://arxiv.org/pdf/1405.4980.pdf
Sébastien Bubeck
Theory Group, Microsoft Research
[email protected]
https://arxiv.org/pdf/1405.4980.pdf
A new paper on learned lossless compression: 30% smaller images than PNG, using a fully parallel probabilistic model that is orders of magnitude faster than PixelCNN
PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"
https://github.com/fab-jul/L3C-PyTorch
PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"
https://github.com/fab-jul/L3C-PyTorch
GitHub
GitHub - fab-jul/L3C-PyTorch: PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"
PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression" - fab-jul/L3C-PyTorch
Very interesting paper from Google Research. Generating video from first and end frames
https://arxiv.org/pdf/1905.10240.pdf
https://arxiv.org/pdf/1905.10240.pdf
Classification Accuracy Score for Conditional Generative Models
Suman Ravuri and Oriol Vinyals: https://arxiv.org/abs/1905.10887
#ArtificialIntelligence #DeepLearning #MachineLearning
Suman Ravuri and Oriol Vinyals: https://arxiv.org/abs/1905.10887
#ArtificialIntelligence #DeepLearning #MachineLearning
Came out a few days back: MNIST test set with extra 50,000 training samples!
If your models overfit the original set, you should try it on this one! ;)
https://www.profillic.com/paper/arxiv:1905.10498
If your models overfit the original set, you should try it on this one! ;)
https://www.profillic.com/paper/arxiv:1905.10498
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…
Chinese AI Talent in Six Charts
Blog by Matt Sheehan: https://macropolo.org/china-ai-research-talent-data/
#ArtificialIntelligence #China #DeepLearning
Blog by Matt Sheehan: https://macropolo.org/china-ai-research-talent-data/
#ArtificialIntelligence #China #DeepLearning
MacroPolo
Chinese AI Talent in Six Charts - MacroPolo
Debates over Chinese and American artificial intelligence (AI) capabilities have been long on bombast and short on data. That’s why at MacroPolo we have created an original dataset based on published papers at what many experts deem the top annual AI conference…
Advanced NLP with spaCy by Ines Montani, core developers of spaCy: https://course.spacy.io
In this course, you'll learn how to use spaCy to build advanced natural language understanding systems, using both rule-based and machine learning approaches.
In this course, you'll learn how to use spaCy to build advanced natural language understanding systems, using both rule-based and machine learning approaches.
Advanced NLP with spaCy
Advanced NLP with spaCy · A free online course
spaCy is a modern Python library for industrial-strength Natural Language Processing. In this free and interactive online course, you'll learn how to use spaCy to build advanced natural language understanding systems, using both rule-based and machine learning…
Creating accurate #MachineLearning Models which are capable of identifying and localizing multiple objects in a single image remained a core challenge in computer vision. But, with recent advancements in #DeepLearning, #ObjectDetection applications are easier to develop than ever before. So, if you want to know how to perform Real-Time Object Detection using #Tensorflow, you can refer to the following article:
https://medium.com/edureka/tensorflow-object-detection-tutorial-8d6942e73adc
https://medium.com/edureka/tensorflow-object-detection-tutorial-8d6942e73adc
Medium
Object Detection Tutorial in TensorFlow- Perform Real-Time Object Detection
This article will provide you with a comprehensive knowledge on Object Detection using one of the best Deep Learning frameworks…
TensorWatch: New debugging and visualization tool designed for deep learning, from Microsoft Research!
Github: https://github.com/microsoft/tensorwatch
Github: https://github.com/microsoft/tensorwatch
GitHub
GitHub - microsoft/tensorwatch: Debugging, monitoring and visualization for Python Machine Learning and Data Science
Debugging, monitoring and visualization for Python Machine Learning and Data Science - microsoft/tensorwatch
“Instead of labeling images, a researcher now simply plays video games all day long.” 🤔
Free supervision from video games
https://bit.do/eTw8d
Free supervision from video games
https://bit.do/eTw8d
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Mingxing Tan and Quoc V. Le: https://arxiv.org/abs/1905.11946
Github: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
Blog: https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html?m=1
#ArtificialIntelligence #MachineLearning #NeuralNetworks
Mingxing Tan and Quoc V. Le: https://arxiv.org/abs/1905.11946
Github: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
Blog: https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html?m=1
#ArtificialIntelligence #MachineLearning #NeuralNetworks
arXiv.org
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically...
Defending Against Neural Fake News
Zellers et al.: https://arxiv.org/abs/1905.12616
#ArtificialIntelligence #DeepLearning #Society
Zellers et al.: https://arxiv.org/abs/1905.12616
#ArtificialIntelligence #DeepLearning #Society
arXiv.org
Defending Against Neural Fake News
Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable...