Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Machine Learning

Machine Learning

Overview of machine learning emphasizing deep learning. Covers Keras example using CIFAR-10 and training and production pipelines.

Melanie Warrick

August 13, 2017
Tweet

More Decks by Melanie Warrick

Other Decks in Technology

Transcript

  1. Machine Learning
    Melanie Warrick
    @nyghtowl

    View full-size slide

  2. @nyghtowl
    Input Computation Result
    Artificial Intelligence

    View full-size slide

  3. @nyghtowl
    AI Fields
    ● Machine Learning
    ● Statistics & Probability Models
    ● Generative & Adversarial Models
    ● Graph Theory
    ● Quantum Computing

    View full-size slide

  4. @nyghtowl
    Artificial Intelligence
    Machine Learning
    Deep
    Learning

    View full-size slide

  5. @nyghtowl
    Machine Learning
    * Rosenfeld Media

    View full-size slide

  6. @nyghtowl
    “DUKE VINCENTIO:
    Well, your wit is in the care of side and that.
    Second Lord:
    They would be ruled after this chamber, and
    my fair nues begun out of the fact, to be
    conveyed,
    Whose noble souls I'll have the heart of the
    wars.
    Clown:
    Come, sir, I will make did behold your worship.
    VIOLA:
    I'll drink it.”
    - Karpathy: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
    - Shakespeare image {{PD-US}}

    View full-size slide

  7. Proprietary & Confidential

    View full-size slide

  8. @nyghtowl
    Machine Learning...

    View full-size slide

  9. @nyghtowl
    ML Algorithms
    ● Linear & Logistic Regression
    ● SVM
    ● Random Forest
    ● Neural Networks
    ● Reinforcement Learning

    View full-size slide

  10. @nyghtowl
    Linear Model / Equation
    y = mx + b
    Linear Regression Model Example
    coefficients

    View full-size slide

  11. @nyghtowl
    Activation Func:
    ● sigmoid
    ● rectified linear
    ● softmax
    ● binary step
    Artificial Neural Net
    y = (W*x + b)

    View full-size slide

  12. @nyghtowl
    Deep Neural Nets
    Hidden
    Input
    Layer 2 Layer 3 Layer 4

    View full-size slide

  13. @nyghtowl
    Convolutional Neural Networks
    Source: mNeuron: A Matlab Plugin to Visualize Neurons from Deep Models, Donglai Wei et. al.

    View full-size slide

  14. @nyghtowl
    Supervised Learning
    Test
    Train

    View full-size slide

  15. @nyghtowl
    Minimize Loss Function
    Loss Functions
    ● mean sqr. error
    ● negative log
    likelihood
    ● cross entropy
    Error
    classific. vs. real label
    dog vs. flower
    Output

    View full-size slide

  16. @nyghtowl
    Optimization | Backprop
    Run until error stops improving = converge
    flower

    View full-size slide

  17. @nyghtowl
    Evaluation
    NN

    View full-size slide

  18. @nyghtowl
    Google Cloud Platform
    Virtual Machines
    Data Storage Analysis & Pipelines
    Machine Learning APIs & Engine w/

    View full-size slide

  19. @nyghtowl
    ML Pipeline | Training
    DB
    Data
    Train
    Algorithm(s)
    Test
    Model
    DB
    Serial
    Model
    Raw
    Data
    Cloud
    SQL
    Compute
    Engine
    protobuf
    Container
    Engine
    Cloud
    Storage
    Cloud
    Dataproc

    View full-size slide

  20. @nyghtowl
    ML Pipeline | Production
    Data
    Serial
    New
    Data
    Model
    Cloud
    Pub/Sub
    Cloud
    Dataflow
    Kafka
    Compute
    Engine
    Container
    Engine
    Mobile apps

    View full-size slide

  21. @nyghtowl
    Machine Learning Pipeline
    DB
    Data
    Train
    Algorithm(s)
    Test
    Model
    DB
    Serial
    Data
    Model
    Serial
    Raw
    Data
    New
    Data
    Model
    Cloud
    Pub/Sub
    Cloud
    Dataflow
    Kafka
    Cloud
    SQL
    Compute
    Engine
    Training
    Production
    protobuf
    Container
    Engine
    Cloud
    Storage
    Cloud
    Dataproc
    Mobile apps

    View full-size slide

  22. @nyghtowl
    Cifar -10
    ● 60K images
    ● 10 classes
    ● 32 x 32 pixels
    (each one is an input)
    - CIFAR-10 http://www.cs.toronto.edu/~kriz/cifar.html | Learning Multiple
    Layers of Features from Tiny Images, Alex Krizhevsky, 2009
    - Kaggle https://www.kaggle.com/c/cifar-10

    View full-size slide

  23. Video Intelligence
    https://github.com/sararob/video-intelligence-demo

    View full-size slide

  24. @nyghtowl
    Last Points
    ML in real world applications
    Leaders in field drive stable solutions
    Never trust the data or models

    View full-size slide

  25. @nyghtowl
    Resources & References
    ● How to run any ML algorithm on GCP nyghtowl.com
    ● Gorner, Martin (2017 Jan 19) Learn TensorFlow and deep learning without a Ph.D.
    https://cloud.google.com/blog/big-data/2017/01/learn-tensorflow-and-deep-learning-without-a-phd
    ● Muic, Tommy (2016 Sep 25) Exception Models explained and implemented
    https://hacktilldawn.com/2016/09/25/inception-modules-explained-and-implemented/
    ● Lewis-Kraus, Gideon (2016 Dec. 14) The Great AI Awakening
    https://www.nytimes.com/2016/12/14/magazine/the-great-ai-awakening.html?smprod=nytcore-ipad&smid=nytcore-ipad-sha
    re&_r=0
    ● Nielsen, Michael Neural Nets and Deep Learning http://neuralnetworksanddeeplearning.com/
    ● Karpathy, Andrej (2015) Hacker’s Guide to Neural Nets https://karpathy.github.io/neuralnets/
    ● Convolutional Networks for Visual Recognition http://cs231n.github.io/
    ● Hobbs, Paul (2013 Oct 4) How can the various machine learning algorithms be classified summarized...
    https://www.quora.com/How-can-the-various-machine-learning-algorithms-be-classified-summarized-according-to-the-probl
    ems-they-solve
    ● Chollet, Francois (2017 July 18) The limitations of deep learning https://blog.keras.io/the-limitations-of-deep-learning.html
    “All code snippets in this presentation are licensed under Apache 2.0 license”
    ● Keras:https://github.com/fchollet/keras/blob/master/examples/cifar10_cnn.py
    ● Keras model to TF:https://github.com/amir-abdi/keras_to_tensorflow/blob/master/keras_to_tensorflow.ipynb

    View full-size slide

  26. @nyghtowl
    References: Images
    ● iStock.com/adventtr
    ● iStock.com/4x-image
    ● iStock.com/vectortatu
    ● iStock.com/d1sk
    ● iStock.com/georgeclerk
    ● iStock.com/JurgaR
    ● iStock.com/ranckreporter
    ● https://static.pexels.com/photos/6069/grass-lawn-green-wooden-6069.jpg
    ● https://www.kaggle.com/c/cifar-10 & http://www.cs.toronto.edu/~kriz/cifar.htm
    ● https://en.wikipedia.org/wiki/Precision_and_recall
    ● https://www.digitaltrends.com/mobile/google-lens-google-io-2017/
    ● Google IO
    ● https://code.flickr.net/2014/10/20/introducing-flickr-park-or-bird/
    ● http://www.texample.net/tikz/examples/neural-network/
    ● http://www.texample.net/tikz/examples/neural-network/
    ● https://en.wikipedia.org/wiki/General_linear_model
    ● https://en.wikipedia.org/wiki/Convolutional_neural_network
    ● https://commons.wikimedia.org/wiki/File:Perceptron.png
    ● https://en.wikipedia.org/wiki/File:Shakes.png
    ● https://www.computer.org/web/awards/pioneer-jean-sammet
    ● Rosenfeld Media https://www.flickr.com/photos/rosenfeldmedia/6949089460
    ● Copyright and disclaimer notice: https://creativecommons.org/licenses/by/2.0/
    ● License notice: https://creativecommons.org/licenses/by/2.0/legalcode

    View full-size slide

  27. @nyghtowl
    Machine Learning
    Melanie Warrick
    @nyghtowl

    View full-size slide