Meta-Sim: Learning to Generate Synthetic Datasets
Kar et al.: https://arxiv.org/abs/1904.11621 @ArtificialIntelligenceArticles
#ComputerVision #PatternRecognition #ArtificialIntelligence
Kar et al.: https://arxiv.org/abs/1904.11621 @ArtificialIntelligenceArticles
#ComputerVision #PatternRecognition #ArtificialIntelligence
Conversation between Lex Fridman and Oriol Vinyals about DeepMind AlphaStar, StarCraft, and Language
Artificial Intelligence podcast: https://youtu.be/Kedt2or9xlo
#AlphaStar #ArtificialIntelligence #DeepLearning #ReinforcementLearning
Artificial Intelligence podcast: https://youtu.be/Kedt2or9xlo
#AlphaStar #ArtificialIntelligence #DeepLearning #ReinforcementLearning
YouTube
Oriol Vinyals: DeepMind AlphaStar, StarCraft, and Language | Lex Fridman Podcast #20
Invertible Residual Networks
Behrmann et al.: https://arxiv.org/abs/1811.00995
#MachineLearning #ArtificialIntelligence #ComputerVision
Behrmann et al.: https://arxiv.org/abs/1811.00995
#MachineLearning #ArtificialIntelligence #ComputerVision
A first in medical robotics: Autonomous navigation inside the body
https://techxplore.com/news/2019-04-medical-robotics-autonomous-body.html?fbclid=IwAR3ragCWgmUkIpQffYdtebY6mnRO7U6d__4uK_nsZKuaoTtv7JHBY0ZNUNo
https://techxplore.com/news/2019-04-medical-robotics-autonomous-body.html?fbclid=IwAR3ragCWgmUkIpQffYdtebY6mnRO7U6d__4uK_nsZKuaoTtv7JHBY0ZNUNo
Techxplore
A first in medical robotics: Autonomous navigation inside the body
Bioengineers at Boston Children's Hospital report the first demonstration of a robot able to navigate autonomously inside the body. In an animal model of cardiac valve repair, the team programmed a robotic ...
Taming Recurrent Neural Networks for Better Summarization
https://www.abigailsee.com/2017/04/16/taming-rnns-for-better-summarization.html
https://www.abigailsee.com/2017/04/16/taming-rnns-for-better-summarization.html
Abigailsee
Taming Recurrent Neural Networks for Better Summarization
<!--excerpt.start-->
<p><em>This blog post is about the <a href=
<p><em>This blog post is about the <a href=
Unsupervised Data Augmentation
Xie et al.: https://arxiv.org/abs/1904.12848
#DeepLearning #MachineLearning #ArtificialIntelligence #UnsupervisedLearning
Xie et al.: https://arxiv.org/abs/1904.12848
#DeepLearning #MachineLearning #ArtificialIntelligence #UnsupervisedLearning
arXiv.org
Unsupervised Data Augmentation for Consistency Training
Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large...
This is lecture 3 in the series on Wasserstein GAN.. In this lecture, basic understanding of Wasserstein Generative Adversarial Network (WGAN) is discussed
https://youtu.be/aenOaiQPSYA
You can subscribe channel for more such videos
https://www.youtube.com/user/kumarahlad/featured?sub_confirmation=1
https://youtu.be/aenOaiQPSYA
You can subscribe channel for more such videos
https://www.youtube.com/user/kumarahlad/featured?sub_confirmation=1
YouTube
Deep Learning 36: (3) Wasserstein Generative Adversarial Network (WGAN): WGAN Understanding
In this lecture, basic understanding of Wasserstein Generative Adversarial Network (WGAN) is discussed
#wasserstein#generative#GAN
#wasserstein#generative#GAN
Claude Shannon, John McCarthy, Ed Fredkin and Joseph Weizenbaum
@ArtificialIntelligenceArticles
#AI in the 60's
@ArtificialIntelligenceArticles
#AI in the 60's
Cornell University - Machine Learning for Intelligent Systems (CS4780/ CS5780)
I highly recommend the Cornell University's "Machine Learning for Intelligent Systems (CS4780/ CS5780)" course taught by Associate Professor Kilian Q. Weinberger.
Youtube Video Lectures:
https://www.youtube.com/playlist?list=PLl8OlHZGYOQ7bkVbuRthEsaLr7bONzbXS
Course Lecture Notes:
https://www.cs.cornell.edu/courses/cs4780/2018fa/lectures/
#artificialintelligence #machinelearning #deeplearning #AI #algorithms #computerscience #datascience
I highly recommend the Cornell University's "Machine Learning for Intelligent Systems (CS4780/ CS5780)" course taught by Associate Professor Kilian Q. Weinberger.
Youtube Video Lectures:
https://www.youtube.com/playlist?list=PLl8OlHZGYOQ7bkVbuRthEsaLr7bONzbXS
Course Lecture Notes:
https://www.cs.cornell.edu/courses/cs4780/2018fa/lectures/
#artificialintelligence #machinelearning #deeplearning #AI #algorithms #computerscience #datascience
YouTube
CORNELL CS4780 "Machine Learning for Intelligent Systems"
Cornell class CS4780. Written lecture notes: https://www.cs.cornell.edu/courses/cs4780/2018fa/lectures/index.html Official class webpage: https://www.cs.cornel...
The once-hot robotics startup Anki is shutting down after raising more than $200 million
It’s a hard, hard fall.
By Theodore Schleifer: https://www.vox.com/2019/4/29/18522966/anki-robot-cozmo-staff-layoffs-robotics-toys-boris-sofman
#ArtificialIntelligence #MachineLearning #Robotics
It’s a hard, hard fall.
By Theodore Schleifer: https://www.vox.com/2019/4/29/18522966/anki-robot-cozmo-staff-layoffs-robotics-toys-boris-sofman
#ArtificialIntelligence #MachineLearning #Robotics
Vox
The once-hot robotics startup Anki is shutting down after raising more than $200 million
It’s a hard, hard fall.
Yining Shi just made three Doodle Classifier experiments with Tensorflow.js:
1. Train a doodle classifier with tf.js
2. Train a doodle classifier with 345 classes
3. KNN doodle classifier
Code and demo: https://github.com/yining1023/doodleNet
#MachineLearning #TensorFlow #tensorflowjs #doodles
1. Train a doodle classifier with tf.js
2. Train a doodle classifier with 345 classes
3. KNN doodle classifier
Code and demo: https://github.com/yining1023/doodleNet
#MachineLearning #TensorFlow #tensorflowjs #doodles
GitHub
GitHub - yining1023/doodleNet: A doodle classifier(CNN), trained on all 345 categories from Quickdraw dataset.
A doodle classifier(CNN), trained on all 345 categories from Quickdraw dataset. - yining1023/doodleNet
Activation Atlases: a new technique for visualizing what interactions between neurons can represent
By Google and OpenAI.
Blog: https://blog.openai.com/introducing-activation-atlases/
Paper: https://distill.pub/2019/activation-atlas
Code: https://github.com/tensorflow/lucid/…
Demo: https://distill.pub/2019/activation-atlas/app.html
#artificialintelligence #deeplearning #machinelearning #neuralnetworks
By Google and OpenAI.
Blog: https://blog.openai.com/introducing-activation-atlases/
Paper: https://distill.pub/2019/activation-atlas
Code: https://github.com/tensorflow/lucid/…
Demo: https://distill.pub/2019/activation-atlas/app.html
#artificialintelligence #deeplearning #machinelearning #neuralnetworks
FOUR Productivity FEYNMAN- strategies:
i) Stop trying to know-it-all.
ii) Don't worry about what others are thinking.
iii) Don't think about what you want to be, but what you want to do.
iv) Have a sense of humor and talk honestly. @ArtificialIntelligenceArticles
i) Stop trying to know-it-all.
ii) Don't worry about what others are thinking.
iii) Don't think about what you want to be, but what you want to do.
iv) Have a sense of humor and talk honestly. @ArtificialIntelligenceArticles
The field of #machinelearning seeks to answer the question "How can we build computer systems that automatically improve with experience, and what are the fundamental laws that govern all learning processes?," Tom Mitchell on the Discipline of Machine Learning
Story: https://mld.ai/6b76a
Paper: https://www.cs.cmu.edu/~tom/pubs/MachineLearning.pdf
#ML #artificialintelligence #research #carnegiemellon #scsatcmu [ machine learning ] [ artificial intelligence ] #AI #education
Story: https://mld.ai/6b76a
Paper: https://www.cs.cmu.edu/~tom/pubs/MachineLearning.pdf
#ML #artificialintelligence #research #carnegiemellon #scsatcmu [ machine learning ] [ artificial intelligence ] #AI #education
A wonderful comprehensive read from #Google_Brain and #DeepmindAI on the challenges which we can come across while implementing RL on real-world systems.
Paper-Title: Challenges of Real-World Reinforcement learning
Link to the paper: https://arxiv.org/abs/1904.12901
They highlighted 9 most important challenges as follows:
1. Training off-line from the fixed logs of an external behavior policy.
2. Learning on the real system from limited samples.
3. High-dimensional continuous state and action spaces.
4. Safety constraints that should never or at least rarely be violated.
5. Tasks that may be partially observable, alternatively viewed as non-stationary or stochastic.
6. Reward functions that are unspecified, multi-objective,or risk-sensitive.
7. System operators who desire explainable policies and actions.
8. Inference that must happen in real-time at the controlfrequency of the system.
9. Large and/or unknown delays in the system actuators,sensors, or rewards.
Paper-Title: Challenges of Real-World Reinforcement learning
Link to the paper: https://arxiv.org/abs/1904.12901
They highlighted 9 most important challenges as follows:
1. Training off-line from the fixed logs of an external behavior policy.
2. Learning on the real system from limited samples.
3. High-dimensional continuous state and action spaces.
4. Safety constraints that should never or at least rarely be violated.
5. Tasks that may be partially observable, alternatively viewed as non-stationary or stochastic.
6. Reward functions that are unspecified, multi-objective,or risk-sensitive.
7. System operators who desire explainable policies and actions.
8. Inference that must happen in real-time at the controlfrequency of the system.
9. Large and/or unknown delays in the system actuators,sensors, or rewards.
arXiv.org
Challenges of Real-World Reinforcement Learning
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL...
Wave Physics as an Analog Recurrent Neural Network
Hughes et al.: https://arxiv.org/abs/1904.12831
#ComputationalPhysics #DeepLearning #MachineLearning #EvolutionaryComputing #Physics
Hughes et al.: https://arxiv.org/abs/1904.12831
#ComputationalPhysics #DeepLearning #MachineLearning #EvolutionaryComputing #Physics
arXiv.org
Wave Physics as an Analog Recurrent Neural Network
Analog machine learning hardware platforms promise to be faster and more energy-efficient than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural candidate...
Performing Structured Improvisations with pre-trained Deep Learning Models
Pablo Samuel Castro: https://arxiv.org/abs/1904.13285
#deeplearning #technology #deepgenerativemodels #machinelearning
Pablo Samuel Castro: https://arxiv.org/abs/1904.13285
#deeplearning #technology #deepgenerativemodels #machinelearning
arXiv.org
Performing Structured Improvisations with pre-trained Deep Learning Models
The quality of outputs produced by deep generative models for music have seen
a dramatic improvement in the last few years. However, most deep learning
models perform in "offline" mode, with few...
a dramatic improvement in the last few years. However, most deep learning
models perform in "offline" mode, with few...
Has anyone checked out MIT's open-sourced introductory course in Deep Learning? Lectures and labs are included:
https://medium.com/tensorflow/mit-introduction-to-deep-learning-4a6f8dde1f0c
https://medium.com/tensorflow/mit-introduction-to-deep-learning-4a6f8dde1f0c
Medium
MIT Introduction to Deep Learning
MIT 6.S191: Introduction to Deep Learning is an introductory course offered formally offered at MIT and open-sourced on the course website…