ArtificialIntelligenceArticles

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

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

487 views15:09

ArtificialIntelligenceArticles

Claude Shannon, John McCarthy, Ed Fredkin and Joseph Weizenbaum
@ArtificialIntelligenceArticles
#AI in the 60's

528 viewsedited 17:22

ArtificialIntelligenceArticles

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

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...

554 views17:31

ArtificialIntelligenceArticles

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

Vox

The once-hot robotics startup Anki is shutting down after raising more than $200 million

It’s a hard, hard fall.

523 views10:42

ArtificialIntelligenceArticles

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

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

445 views10:45

ArtificialIntelligenceArticles

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

468 views11:04

ArtificialIntelligenceArticles

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

641 viewsedited 17:19

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

478 viewsedited 17:20

ArtificialIntelligenceArticles

#ArtificialIntelligence #DeepLearning #MachineLearning

467 views17:27

ArtificialIntelligenceArticles

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.

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...

512 views18:55

ArtificialIntelligenceArticles

Wave Physics as an Analog Recurrent Neural Network
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...

457 views00:50

ArtificialIntelligenceArticles

Performing Structured Improvisations with pre-trained Deep Learning Models
Pablo Samuel Castro: https://arxiv.org/abs/1904.13285
#deeplearning #technology #deepgenerativemodels #machinelearning