# 10 More Cool Deep Learning Applications | Two Minute Papers #52

## Метаданные

- **Канал:** Two Minute Papers
- **YouTube:** https://www.youtube.com/watch?v=hPKJBXkyTKM
- **Дата:** 13.03.2016
- **Длительность:** 3:57
- **Просмотры:** 105,844
- **Источник:** https://ekstraktznaniy.ru/video/14859

## Описание

In this episode, we present another round of incredible deep learning applications!

_________________________

1. Colorization - http://tinyclouds.org/colorize/
2. RNN Music on Bob Sturm's YouTube channel - https://www.youtube.com/watch?v=RaO4HpM07hE
3. Flow Machines by Sony - https://www.youtube.com/watch?v=buXqNqBFd6E
4. RNN Passwords - https://github.com/gehaxelt/RNN-Passwords
5. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding - http://arxiv.org/abs/1510.00149
6. Right Whale Kaggle Competition - http://felixlaumon.github.io/2015/01/08/kaggle-right-whale.html
7. Improving YouTube video thumbnails - http://youtube-eng.blogspot.hu/2015/10/improving-youtube-video-thumbnails-with_8.html
8. Celebrity super-resolution: https://github.com/mikesj-public/dcgan-autoencoder
9. Convolutional Neural Network visualization - http://scs.ryerson.ca/~aharley/vis/conv/ + Paper: http://scs.ryerson.ca/~aharley/vis/harley_vis_isvc15.pdf
10. DarkNet

## Транскрипт

### Intro []

dear fellow scholars this is two minute papers with károly if I hear to all of you fellow scholars out there who are yearning for some more deep learning action like I do here goes the second package buckle up amazing applications await you as always links to every one of these works are available in the description box this convolutional neural network can learn how to colorize by looking at the same images both in color and black and white the first image is the black and white input the second is how the algorithm colorized it and the third is how the image originally looked like in color insanity

### Music Generation [0:37]

recurrent neural networks are able to learn and produce sequences of data and they are getting better and better at music generation nowadays people are experimenting with human aided music generation with pretty amazing results sony has also been working on such a

### Leaked passwords [1:05]

solution with spectacular results one can also run a network on a large database of leaked human passwords and try to crack new accounts building on that knowledge deep neural networks take a substantial amount of time to train and the final content of each of the neurons have to be stored which takes a lot of space new techniques are being explored to compress the information content of these networks there is another application where endangered whale species are recognized by convolutional neural networks some of them have a worldwide population of less than 500 and this is where machine learning steps in to try to save them

### YouTube thumbnails [2:21]

awesome YouTube has a huge database full of information on what kind of video thumbnails are the ones that people end up clicking on they use deep learning to automatically find and suggest the most appealing images for your videos there is also this crazy application where a network was trained on a huge data set with images of celebrities a low-quality image is given where the algorithm creates a higher resolution version building on this knowledge the leftmost images are the true high resolution images the second one is the grainy low resolution input and the third is the neural networks attempt to reconstruct the original

### Neural Networks [3:00]

this application takes your handwriting of a number and visualizes how a convolutional neural network understands and classifies it

### Outro [3:16]

apparently george RR martin is late with writing the next book of game of thrones but luckily we have recurrent neural networks that can generate text in his style an infinite amount so beware George winter is coming I mean the machines are coming it is truly amazing what these techniques are capable of and as machine learning is a remarkably fast-moving field new applications pop up pretty much every day I am quite enthused to do at least one more batch of these of course provided that you like this one let me know thanks for watching and for your generous support and I'll see you next time