Training Deep Neural Networks With Dropout | Two Minute Papers #62

Channel:
Hungary Two Minute Papers
Subscribers:
1,550,000
Published on ● Video Link: https://www.youtube.com/watch?v=LhhEv1dMpKE


Duration: 3:29
9,101 views
289

In this episode, we discuss the bane of many machine learning algorithms - overfitting. It is also explained why it is an undesirable way to learn and how to combat it via dropout.

_____________________

The paper "Dropout: A Simple Way to Prevent Neural Networks from
Overtting" is available here:
https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf

Andrej Karpathy's autoencoder is available here:
http://cs.stanford.edu/people/karpathy/convnetjs/demo/autoencoder.html

Recommended for you:
Overfitting and Regularization For Deep Learning - https://www.youtube.com/watch?v=6aF9sJrzxaM
Decision Trees and Boosting, XGBoost -https://www.youtube.com/watch?v=0Xc9LIb_HTw
A full playlist with machine learning and deep learning-related Two Minute Papers videos - https://www.youtube.com/playlist?list=PLujxSBD-JXglGL3ERdDOhthD3jTlfudC2

WE WOULD LIKE TO THANK OUR GENEROUS SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE:
Sunil Kim, Vinay S.
https://www.patreon.com/TwoMinutePapers

Subscribe if you would like to see more of these! - http://www.youtube.com/subscription_center?add_user=keeroyz

The thumbnail image background was created by Norma (CC BY 2.0) - https://flic.kr/p/ejXPXt
Splash screen/thumbnail design: Felícia Fehér - http://felicia.hu

Károly Zsolnai-Fehér's links:
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


2016-06-08Image Colorization With Deep Learning and Classification | Two Minute Papers #71
2016-06-05Schrödinger's Smoke | Two Minute Papers #70
2016-05-30Storytime & Reading Comments | Two Minute Papers
2016-05-25Surface-Only Liquids | Two Minute Papers #69
2016-05-22Artistic Style Transfer For Videos | Two Minute Papers #68
2016-05-19Deep Reinforcement Terrain Learning | Two Minute Papers #67
2016-05-15Separable Subsurface Scattering | Two Minute Papers #66
2016-05-11Real-Time Shading With Area Light Sources | Two Minute Papers #65
2016-05-08Deep Learning and Cancer Research | Two Minute Papers #64
2016-05-04Face2Face: Real-Time Facial Reenactment
2016-05-01Training Deep Neural Networks With Dropout | Two Minute Papers #62
2016-04-28Narrow Band Liquid Simulations | Two Minute Papers #61
2016-04-24No Such Thing As Artificial Intelligence | Two Minute Papers #60
2016-04-1410 Even Cooler Deep Learning Applications | Two Minute Papers #59
2016-04-10The Dunning-Kruger Effect | Two Minute Papers #58
2016-04-04From Doodles To Paintings With Deep Learning | Two Minute Papers #57
2016-03-30Overfitting and Regularization For Deep Learning | Two Minute Papers #56
2016-03-27How The Witness Teaches Scientific Thinking
2016-03-24Decision Trees and Boosting, XGBoost | Two Minute Papers #55
2016-03-203D Depth From a Single Photograph | Two Minute Papers #54
2016-03-15How DeepMind's AlphaGo Defeated Lee Sedol | Two Minute Papers #53


Tags:
two minute papers
dropout
l1 regularization
l2 regularization
deep learning regularization
deep learning overfitting
neural network overfitting
machine learning overfitting
neural network regularization
what to do overfitting
deep neural network overfitting
deep learning regularizer
dropconnect
neural network dropout
underfitting
overfit
deep learning dropout
regularization with dropout
Dropout: A Simple Way to Prevent Neural Networks from Over tting
overfitting