Oleg Zabluda's blog
Monday, February 19, 2018
 
Learning Features of Music from Scratch
Learning Features of Music from Scratch
"""
This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research. MusicNet consists of hundreds of freely-licensed classical music recordings by 10 composers, written for 11 instruments, together with instrument/note annotations resulting in over 1 million temporal labels on 34 hours of chamber music performances under various studio and microphone conditions.

The paper defines a multi-label classification task to predict notes in musical recordings, along with an evaluation protocol, and benchmarks several machine learning architectures for this task: i) learning from spectrogram features; ii) end-to-end learning with a neural net; iii) end-to-end learning with a convolutional neural net. These experiments show that end-to-end models trained for note prediction learn frequency selective filters as a low-level representation of audio.
"""
https://arxiv.org/abs/1611.09827

https://arxiv.org/abs/1611.09827

Labels:


- posted by Oleg Zabluda @ 6:25 PM | permalink | | | technorati | bloglines | feedster
 
Measuring the Progress of AI Research
Measuring the Progress of AI Research
https://www.eff.org/ai/metrics
https://www.eff.org/ai/metrics

Labels:


- posted by Oleg Zabluda @ 6:05 PM | permalink | | | technorati | bloglines | feedster
 
Use random linear interpolation for data & labels to improve stuff
Use random linear interpolation for data & labels to improve stuff

mixup: Beyond Empirical Risk Minimization (1017)
"""
mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple linear behavior in-between training examples. Our experiments on the ImageNet-2012, CIFAR-10, CIFAR-100, Google commands and UCI datasets show that mixup improves the generalization of state-of-the-art neural network architectures. We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.
"""
https://arxiv.org/abs/1710.09412v1
https://arxiv.org/abs/1710.09412v1

Labels:


- posted by Oleg Zabluda @ 1:54 PM | permalink | | | technorati | bloglines | feedster
 
Псой Короленко - "Ужасным способом 3 раза"
Псой Короленко - "Ужасным способом 3 раза"
https://www.youtube.com/watch?v=_XaZERPSt_Q
https://www.youtube.com/watch?v=_XaZERPSt_Q

Labels:


- posted by Oleg Zabluda @ 12:15 PM | permalink | | | technorati | bloglines | feedster
 
Стиляги (фильм, 2008)
Стиляги (фильм, 2008)
"""
Мэл...
У меня для тебя плохие новости.
Там [в Америке] нет стиляг.
[...]
Но мы-то есть.
"""
http://vvord.ru/tekst-filma/Stilyagi/8
http://vvord.ru/tekst-filma/Stilyagi/8

Labels:


- posted by Oleg Zabluda @ 11:58 AM | permalink | | | technorati | bloglines | feedster
 
Western Digital Stuns Storage Industry with MAMR Breakthrough for Next-Gen HDDs
Western Digital Stuns Storage Industry with MAMR Breakthrough for Next-Gen HDDs
https://www.anandtech.com/print/11925/western-digital-stuns-storage-industry-with-mamr-breakthrough-for-nextgen-hdds

https://www.anandtech.com/show/11925/western-digital-stuns-storage-industry-with-mamr-breakthrough-for-nextgen-hdds

Labels:


- posted by Oleg Zabluda @ 9:56 AM | permalink | | | technorati | bloglines | feedster

Powered by Blogger