Neural Programmer-Interpreters Learn To Write Programs | Two Minute Papers #34

Channel:
Hungary Two Minute Papers
Subscribers:
1,720,000
Published on ● Video Link: https://www.youtube.com/watch?v=B70tT4WMyJk


Duration: 2:43
12,652 views
360

In machine learning, we usually have a set of problems for which we are looking for solutions. For instance, "here is an image, please tell me what is seen on it". Or, "here is a computer game, please beat level three". One problem, one solution. In this case, we are not looking for one solution, we are looking for a computer program, an algorithm, that can solve any number of problems of the same kind. It can also learn how to rotate images of different cars around to obtain a frontal pose. This technique can learn from someone how to sort a set of 20 numbers and generalize its knowledge to much longer sequences.

______________________

The paper "Neural Programmer-Interpreters" is available here:
http://www-personal.umich.edu/~reedscot/iclr_project.html

The thumbnail image was created by Iwan Gabovitch (CC BY 2.0) - https://flic.kr/p/paxzB9
Subscribe if you would like to see more of these! - http://www.youtube.com/subscription_center?add_user=keeroyz

Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu

Károly Zsolnai-Fehér's links:
Patreon → https://www.patreon.com/TwoMinutePapers
Facebook → https://www.facebook.com/TwoMinutePapers/
Twitter → https://twitter.com/karoly_zsolnai
Web → https://cg.tuwien.ac.at/~zsolnai/



Other Videos By Two Minute Papers


2016-02-06Extrapolations and Crowdfunded Research (Experiment) | Two Minute Papers #44
2016-02-03Breaking Deep Learning Systems With Adversarial Examples | Two Minute Papers #43
2016-01-31How DeepMind Conquered Go With Deep Learning (AlphaGo) | Two Minute Papers #42
2016-01-27What Do Virtual Objects Sound Like? | Two Minute Papers #41
2016-01-24Simulating Viscosity and Melting Fluids | Two Minute Papers #40
2016-01-20Interactive Editing of Subsurface Scattering | Two Minute Papers #39
2016-01-173D Printing Objects With Caustics | Two Minute Papers #38
2016-01-12Designing 3D Printable Robotic Creatures | Two Minute Papers #37
2016-01-09Designing Cities and Furnitures With Machine Learning | Two Minute Papers #36
2016-01-059 Cool Deep Learning Applications | Two Minute Papers #35
2015-12-31Neural Programmer-Interpreters Learn To Write Programs | Two Minute Papers #34
2015-12-24Peer Review #1 [Audio only] | Two Minute Papers
2015-12-20Painting with Fluid Simulations | Two Minute Papers #33
2015-12-16How Do Genetic Algorithms Work? | Two Minute Papers #32
2015-12-12OpenAI - Non-profit AI company by Elon Musk and Sam Altman
2015-12-10Randomness and Bell's Inequality [Audio only] | Two Minute Papers #31
2015-12-03Automatic Parameter Control for Metropolis Light Transport | Two Minute Papers #30
2015-11-29Artificial Superintelligence [Audio only] | Two Minute Papers #29
2015-11-25Are We Living In a Computer Simulation? | Two Minute Papers #28
2015-11-22Google DeepMind's Deep Q-Learning & Superhuman Atari Gameplays | Two Minute Papers #27
2015-11-21Multiple-Scattering Microfacet BSDFs with the Smith Model


Tags:
two minute papers
deep learning
machine learning
Neural Programmer-Interpreters
Neural Programmer Interpreter
recurrent neural network
lstm
long short term memory
sepp hochreiter
Scott Reed
Nando de Freitas
google deepmind
deepmind
artificial intelligence
bubble sort
machine learning bubble sort
neural network sort
neural network sorting
neural network bubble sort
learning sorting