DeepLearning

Artigos Interessantes

• Neural Networks Tutorial – A Pathway to Deep Learning http://adventuresinmachinelearning.com/neural-networks-tutorial/
• Music transcription modelling and composition using deep learnin https://arxiv.org/abs/1604.08723
• Text generation using deep recurrent neural networks http://deeplearningathome.com/2016/10/Text-generation-using-deep-recurrent-neural-networks.html
• Composing Music With Recurrent Neural Networks http://www.hexahedria.com/2015/08/03/composing-music-with-recurrent-neural-networks/
• A Step by Step Backpropagation Example https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/
• Not another MNIST tutorial with TensorFlow https://www.oreilly.com/learning/not-another-mnist-tutorial-with-tensorflow
• Open Source Machine Learning Degree http://www.kdnuggets.com/2016/06/open-source-machine-learning-degree.html?utm_content=buffer7b7c4&utm_medium=social&utm_source=facebook.com&utm_campaign=buffer
• Top 10 IPython Notebook Tutorials for Data Science and Machine Learning http://www.kdnuggets.com/2016/04/top-10-ipython-nb-tutorials.html
• A Neural Network in 11 lines of Python (Part 1) http://iamtrask.github.io/2015/07/12/basic-python-network/
• Deep Learning: Language identification using Keras & TensorFlow http://machinelearningexp.com/
• Teaching Deep Learning http://p.migdal.pl/2017/04/30/teaching-deep-learning.html
• Data Science & Tech Projects http://francescopochetti.com/portfoliodata-science-machine-learning/
• Técnicas de Aprendizado de Máquina https://matheusfacure.github.io/tutorials/
• Gradiente Local http://www.professores.uff.br/jmarcos/images/stories/Disciplinas/RedesNeurais/Perceptrons2.pdf

Backprogation

• A Neural Network in Python, Part 1: sigmoid function, gradient descent & backpropagation http://python3.codes/neural-network-python-part-1-sigmoid-function-gradient-descent-backpropagation/
• Deep Neural Network from scratch https://matrices.io/deep-neural-network-from-scratch/
• Yes you should understand backprop https://medium.com/@karpathy/yes-you-should-understand-backprop-e2f06eab496b

Data Augmentation

• What you need to know about data augmentation for machine learning https://cartesianfaith.com/2016/10/06/what-you-need-to-know-about-data-augmentation-for-machine-learning/
• Audio Augmentation for Speech Recognition http://speak.clsp.jhu.edu/uploads/publications/papers/1050_pdf.pdf
• Keras ImageDataGenerator https://keras.io/preprocessing/image/

TensorFlow

• 10 minutes Practical TensorFlow Tutorial for quick learners http://cv-tricks.com/artificial-intelligence/deep-learning/deep-learning-frameworks/tensorflow-tutorial/

• Livro: First Contact With TensorFlow http://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/first-contact-with-tensorflow/#cap5

• tutoriais tensorflow: https://github.com/pkmital/tensorflow_tutorials https://github.com/jtoy/awesome-tensorflow https://github.com/aymericdamien/TensorFlow-Examples

Livros:

• Deep Learning Methods and Applications Li Deng and Dong Yu https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/DeepLearning-NowPublishing-Vol7-SIG-039.pdf

Datasets

• http://deeplearning.net/datasets/
• http://pandawhale.com/post/44498/deep-learning-datasets
• http://www.cs.jhu.edu/~mdredze/code.php
• https://catalog.ldc.upenn.edu/LDC93S1
• https://medium.com/startup-grind/fueling-the-ai-gold-rush-7ae438505bc2#.lvq7uy9v1
• http://www.openslr.org/12/
• https://docs.google.com/spreadsheets/d/1AQvZ7-Kg0lSZtG1wlgbIsrm90HaTZrJGQMz-uKRRlFw/htmlview
• http://meiobit.com/357253/microsoft-libera-banco-de-dados-inteligencia-artificial-com-100-mil-perguntas-repositorio-msmarco-cortana-bing/
• http://www.voxforge.org/pt/downloads
• http://qt21.metashare.ilsp.gr/repository/download/49380cd244e711e5ba5300155d01190440bfbb69739143688b252b5f9cc2128e/
• https://catalog.ldc.upenn.edu/LDC2008S04#
• http://www.linguateca.pt/corpora_info.html#cor3fal
• http://www.c-oral-brasil.org/
• http://rodrigob.github.io/are_we_there_yet/build/#datasets
• MusicNet http://homes.cs.washington.edu/~thickstn/musicnet.html
• Classical Guitar MIDI http://www.classicalguitarmidi.com/index.html
• 11 bases de dados gratuitas para mineração, estudos e testes http://www.bigdatabusiness.com.br/6-bases-de-dados-gratuitas-para-mineracao-estudos-e-testes/

Speech Recognition

• https://github.com/Uberi/speech_recognition
• Awesome Recurrent Neural Networks https://github.com/kjw0612/awesome-rnn
• http://cmusphinx.sourceforge.net/
• An attempt at tracking states of the art(s) and recent results on speech recognition. https://github.com/cmusphinx/wer_are_we
• Towards End-to-End Speech Recognition with Recurrent Neural Networks http://www.jmlr.org/proceedings/papers/v32/graves14.pdf

MFCC

• Implementação em Python http://pydoc.net/Python/scikits.talkbox/0.2.3/scikits.talkbox.features.mfcc/
• Biblioteca https://github.com/jameslyons/python_speech_features
• Mel Frequency Cepstral Coefficients (MFCCs) http://musicinformationretrieval.com/mfcc.html

Autoencoders

• Building Autoencoders in Keras https://blog.keras.io/building-autoencoders-in-keras.html

LSTM

• Um guia de noob para implementar RNN-LSTM usando Tensorflow http://monik.in/a-noobs-guide-to-implementing-rnn-lstm-using-tensorflow/
• A Eficácia Irracional das Redes Neurais Recorrentes http://karpathy.github.io/2015/05/21/rnn-effectiveness/
• Introduction to Recurrent Networks in TensorFlow http://www.kdnuggets.com/2016/05/intro-recurrent-networks-tensorflow.html
• Backpropogating an LSTM: A Numerical Example (O melhor exemplo que já encontrei) https://medium.com/@aidangomez/let-s-do-this-f9b699de31d9
• Understanding LSTM and its diagrams https://medium.com/@shiyan/understanding-lstm-and-its-diagrams-37e2f46f1714
• How to build a Recurrent Neural Network in TensorFlow (1/7) https://medium.com/@erikhallstrm/hello-world-rnn-83cd7105b767
• Understanding LSTM and its diagrams https://medium.com/@shiyan/understanding-lstm-and-its-diagrams-37e2f46f1714
• https://medium.com/tag/lstm
• A noob’s guide to implementing RNN-LSTM using Tensorflow https://medium.com/@monikkinom/a-noobs-guide-to-implementing-rnn-lstm-using-tensorflow-1907a5bbb1fa
• Char-rnn http://blog.adammenges.com/char-rnn/
• Rohan & Lenny #3: Recurrent Neural Networks & LSTMs https://ayearofai.com/rohan-lenny-3-recurrent-neural-networks-10300100899b
• LSTM Forward and Backward Pass - http://arunmallya.github.io/writeups/nn/lstm/index.html#/ http://arunmallya.github.io/
• RECURRENT NEURAL NETWORKS (RNN) – PART 1: BASIC RNN / CHAR-RNN https://theneuralperspective.com/2016/10/04/05-recurrent-neural-networks-rnn-part-1-basic-rnn-char-rnn/
• Simple LSTM - http://nicodjimenez.github.io/2014/08/08/lstm.html
• Exploring LSTMs - http://blog.echen.me/2017/05/30/exploring-lstms/
• Vários materiais de LSTM - http://www.cs.toronto.edu/~graves/
• https://stackoverflow.com/questions/43034960/many-to-one-and-many-to-many-lstm-examples-in-keras
• MASKED BIDIRECTIONAL LSTMS WITH KERAS

LSTM and Music Composition

• https://maraoz.com/2016/02/02/abc-rnn/
• http://cslab1.bc.edu/~csacademics/pdf/16Mikami.pdf
• dataset http://abc.sourceforge.net/NMD/
• https://cs.adelaide.edu.au/~markus/pub/2008evomusart.pdf
• https://highnoongmt.wordpress.com/2015/08/15/deep-learning-for-assisting-the-process-of-music-composition-part-4/
• https://github.com/MattVitelli/GRUV
• http://www.hexahedria.com/files/2017generatingpolyphonic.pdf
• Polyphonic Music Generation Using Tied Parallel Networksh ttps://www.cs.hmc.edu/~ddjohnson/tied-parallel/
• conversor abc para MIDI http://colinhume.com/music.aspx
• Free XML Music View https://www.soundslice.com/musicxml-viewer/
• Biaxial Recurrent Neural Network for Music Composition https://github.com/hexahedria/biaxial-rnn-music-composition
• DataSet MusicXML https://github.com/grant/algo-rhythm http://openmusicscore.org/
• Algo Rhythm: Music Composition using Neural Networks https://medium.com/@granttimmerman/algo-rhythm-music-composition-using-neural-networks-f89897ff2df7
• Musical TensorFlow, Part 1 - How to build an RBM in TensorFlow for making music http://danshiebler.com/2016-08-10-musical-tensorflow-part-one-the-rbm/
• Music RNN RBM = https://github.com/dshieble/Music_RNN_RBM
• Metis Final Project: Music Composition with LSTMs http://blog.naoya.io/metis-final-project-music-composition-with-lstms/
• DeepHear - Composing and Harmonizing Music with Neural http://www.gitxiv.com/posts/kZz9PCRcktdYSrWnp/deephear-composing-and-harmonizing-music-with-neural
• deep learning for music https://amundtveit.com/2016/11/22/deep-learning-for-music/
• Explanation Music Generation https://github.com/unnati-xyz/music-generation/wiki/Explanation
• Generating Multi-track Music with Deep Learning https://alexprevoteau.com/2016/11/23/generating-multi-track-music-with-deep-learning/
• Generating Long-Term Structure in Songs and Stories https://magenta.tensorflow.org/2016/07/15/lookback-rnn-attention-rnn/
• Modelling Symbolic Music: Beyond the Piano Roll https://arxiv.org/abs/1606.01368
• Polyphonic Music Generation Using Tied Parallel Networks https://www.cs.hmc.edu/~ddjohnson/tied-parallel/
• RNN Music Composer (slide) http://imatv.me/classes/Psych186BClassSlidesRNNMusic.pdf
• Tradução Neural de Estilo Musical http://imanmalik.com/cs/2017/06/05/neural-style.html
• Geração Automática de Acompanhamento com Seq2Seq http://qihqi.github.io/machine/learning/music-generation-using-rnn/
• Deep Remix http://deepremix.com/
• Music Language Modeling with Recurrent Neural Networks http://yoavz.com/music_rnn/
• SCHUMANN: REDES NEURAIS RECORRENTES QUE COMPÕEM MÚSICA http://inspiratron.org/blog/2017/01/01/schumann-rnn-composing-music/
• Aprender a compor música de arquivos MIDI usando uma rede neural LSTM em deeplearning4j https://github.com/deeplearning4j/dl4j-examples/tree/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/recurrent/character/melodl4j
• An improvisational AI that unleashes the creative power of an entire orchestra to music producers and artists https://devpost.com/software/orchestrai
• Many to one and many to many LSTM examples in Keras https://stackoverflow.com/questions/43034960/many-to-one-and-many-to-many-lstm-examples-in-keras

GAN

• Course:CPSC522/Generative Adversarial Networks - http://wiki.ubc.ca/Course:CPSC522/Generative_Adversarial_Networks#Some_sampling_results
• CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms https://arxiv.org/abs/1706.07068
• CAN (Creative Adversarial Network) - Explained - http://www.kdnuggets.com/2017/07/creative-adversarial-network.html
• GAN by Example using Keras on Tensorflow Backend https://medium.com/towards-data-science/gan-by-example-using-keras-on-tensorflow-backend-1a6d515a60d0

CNN

• Treinando sua primeira CNN https://gurus.pyimagesearch.com/lesson-sample-training-your-first-cnn/
• Convolutional Neural Networks Tutorial in TensorFlow http://adventuresinmachinelearning.com/convolutional-neural-networks-tutorial-tensorflow/
• http://arunmallya.github.io/

Papers Music Generation

• Music Generation with Deep Learning https://arxiv.org/abs/1612.04928
• Deep Learning for Music https://arxiv.org/pdf/:1606.04930v1.pdf?
• WAVENET: A GENERATIVE MODEL FOR RAW AUDIO https://arxiv.org/pdf/:1609.03499v2.pdf?
• using machine learning to generate music http://www.datasciencecentral.com/profiles/blogs/using-machine-learning-to-generate-music
• MidiNet Demo - learning to generate music from MIDI tabs. https://richardyang40148.github.io/TheBlog/index.html - https://arxiv.org/pdf/1703.10847v1.pdf
• Musica Fractal - http://www.educ.fc.ul.pt/icm/icm99/icm14/musica_fractal.htm

Processamento de Audio

• http://www.ifs.tuwien.ac.at/~schindler/lectures/MIR_Feature_Extraction.html
• midi note numbers http://www.electronics.dit.ie/staff/tscarff/Music_technology/midi/midi_note_numbers_for_octaves.htm
• Discrete FourierTransform (DFT) http://homes.ieu.edu.tr/skondakci/courses/CE476/frequency%20spectrum%20with%20scipy.pdf

Probabilidade

• Teorema de Bayes http://www.monografias.com/trabajos89/probabilidad-total-y-teorema-bayes/probabilidad-total-y-teorema-bayes.shtml
• 5. Naive Bayes https://www.vooo.pro/insights/fundamentos-dos-algoritmos-de-machine-learning-com-codigo-python-e-r/

Algebra Linear

• Linear algebra cheat sheet for deep learning https://medium.com/towards-data-science/linear-algebra-cheat-sheet-for-deep-learning-cd67aba4526c

Theano

• Theano Tutorial - http://www.marekrei.com/blog/theano-tutorial/

2017-02-17

• TensorFlow-Tutorials https://github.com/nlintz/TensorFlow-Tutorials
• Awesome Recurrent Neural Networks https://github.com/kjw0612/awesome-rnn
• How to implement a neural network http://peterroelants.github.io/

2017-02-15

• deep_recommend_system https://github.com/tobegit3hub/deep_recommend_system

2017-02-11

• 13 Free Self-Study Books on Mathematics, Machine Learning & Deep Learning http://blog.hackerearth.com/13-free-self-study-books-mathematics-machine-learning-deep-learning?utm_source=facebook-post&utm_campaign=hack-heart&utm_medium=he-handle

2017-02-07

• Deep Learning for Natural Language Processing: https://github.com/oxford-cs-deepnlp-2017/lectures http://memkite.com/deep-learning-bibliography/#2014ZHuangMDongQMaoYZhan
• DEEPLEARNING.UNIVERSITY – AN ANNOTATED DEEP LEARNING BIBLIOGRAPHY http://memkite.com/deep-learning-bibliography/#music

2017-02-06

• Comandos úteis de gerenciamento do docker https://www.eduardomedeiros.me/docker-comandos/

2017-02-03

• https://github.com/kaleko/CourseraML
• 6.S191: Introduction to Deep Learning http://introtodeeplearning.com/index.html

2017-02-02

• Disciplina: Redes Neurais Profundas (Deep Learning) [Professor: Anderson da Silva Soares]

2017-02-01

• RECURRENT NEURAL NETWORKS TUTORIAL, PART 1 – INTRODUCTION TO RNNS (http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/)]

• Deeplearning Paper Notes [github]

2017-01-23

• Projetos interessantes [DeepSpeech] e [speech-recognition]
• Traffic signs classification with Deep Learning https://hackernoon.com/traffic-signs-classification-with-deep-learning-b0cb03e23efb#.omgdirjrz
• https://highnoongmt.wordpress.com/2015/08/15/deep-learning-for-assisting-the-process-of-music-composition-part-4/

Speeach Recognition

• https://github.com/VikParuchuri/scribe
• http://surguy.net/articles/speechrecognition.xml
• https://thenerdshow.com/freespeech.html
• http://cmusphinx.sourceforge.net/
• https://jugad2.blogspot.com.br/2014/03/speech-recognition-with-python-speech.html
• http://code.activestate.com/recipes/579115-recognizing-speech-speech-to-text-with-the-python-/
• https://pypi.python.org/pypi/SpeechRecognition/
• https://github.com/DelightRun/PyBaiduYuyin
• https://github.com/Uberi/speech_recognition#readme
• https://github.com/michaelgundlach/pyspeech
• https://sourceforge.net/projects/kaldi/
• http://memkite.com/blog/2015/02/11/deep-learning-for-speech-recognition/

Instalação de bibliotecas

• conda install -c bokeh pyaudio=0.2.7
• pip install grpcio
• pip install webrtcvad
• pip install numpy
• pip install tensorflow
• music21 $ sudo pip install https://github.com/cuthbertLab/music21/releases/download/v3.1.0/music21-3.1.0.tar.gz
• PYGAME $ sudo pip install pygame --user

fazer o jupyter enxergar o kernel do ambiente criado no conda, deve instalar dentro do ambiente

• source activate teste
• conda install jupyter