Technology
Convolutional nets are great for image classification... if this were 2016. But it's 2018 and Canada's greatest neural networker Geoff Hinton has some new ideas, namely capsule networks. Capsule nets are a completely new type of neural net architecture designed to do image classification on far fewer training cases than convolutional nets, and they're posting results that are competitive with much more mature technologies.
In this episode, we'll give a light conceptual introduction to capsule nets and get geared up for a future episode that will do a deeper technical dive.
view more
More Episodes
Google Flu Trends
2018-03-26
2018-03-26
Autoencoders
2018-03-12
2018-03-12
When Private Data Isn't Private Anymore
2018-03-05
2018-03-05
Open Data and Open Science
2018-02-19
2018-02-19
Auto-generating websites with deep learning
2018-02-04
2018-02-04
The Fourier Transform
2018-01-08
13
2018-01-08
13
Statistics of Beer
2018-01-02
31
2018-01-02
31
Re - Release: Random Kanye
2017-12-24
17
2017-12-24
17
Debiasing Word Embeddings
2017-12-18
40
2017-12-18
40
The Kernel Trick and Support Vector Machines
2017-12-11
54
2017-12-11
54
Maximal Margin Classifiers
2017-12-04
47
2017-12-04
47
Re - Release: The Cocktail Party Problem
2017-11-27
30
2017-11-27
30
Clustering with DBSCAN
2017-11-20
37
2017-11-20
37
The Kaggle Survey on Data Science
2017-11-13
56
2017-11-13
56
Get this podcast on your
phone, FREE
