Vermont Code Camp 2019 - Intro to Deep Learning for Developers

For Vermont locals:
Join the BTV Dev Slack Community! http://btvdev-slackin.herokuapp.com/
Vermont Women in Machine Learning and Data Science Meetup - https://www.meetup.com/VT-WiMLDS/
Burlington Data Scientists Meetup - https://www.meetup.com/Burlington-Data-Scientists/

Talk Resources:
*Machine Learning Frameworks*
TensorFlow - https://www.tensorflow.org/
Train your first neural network: basic classification | TensorFlow -https://www.tensorflow.org/tutorials/keras/basic_classification
Keras - https://keras.io/
PyTorch - https://pytorch.org/
Caffe2 - https://caffe2.ai/

*Resources on IBM Developer*
IBM Developer - https://developer.ibm.com/
IBM Cloud - https://ibm.biz/BdzXfW
Center for Open-Source Data & AI Technologies (CODAIT) - http://codait.org/
IBM Developer Model Asset Exchange (MAX) - https://developer.ibm.com/exchanges/models/
Model Asset Exchange (MAX) Code Patterns - https://developer.ibm.com/patterns/category/model-asset-exchange/
🧙😺 magicat - https://github.com/CODAIT/magicat
Veremin - https://veremin.mybluemix.net/

*Preparing, Building, and Training AI Models*
Project Jupyter - https://jupyter.org/
IBM Developer Model Asset Exchange (MAX) - https://developer.ibm.com/exchanges/models/
IBM Watson Knowledge Catalog - https://www.ibm.com/cloud/watson-knowledge-catalog
IBM Watson Studio - https://www.ibm.com/cloud/watson-studio

*Deploying and Running AI Models*
Data Mining Group (PMML & PFA) - http://dmg.org/
ONNX - https://onnx.ai/
ONNX.js - https://github.com/Microsoft/onnxjs
TensorFlow.js - https://js.tensorflow.org/
TensorFlow Lite - https://www.tensorflow.org/lite
Core ML - https://developer.apple.com/machine-learning/
IBM Watson Machine Learning - https://www.ibm.com/cloud/machine-learning

*Operating, Managing, and Making AI Systems Explainable, Fair, and Robust*
Fabric for Deep Learning (FfDL) - https://github.com/IBM/FfDL
AI Fairness 360 Toolkit - https://github.com/IBM/AIF360
Adversarial Robustness 360 Toolbox - https://github.com/IBM/adversarial-robustness-toolbox
AI Explainability 360 Toolkit - https://github.com/IBM/AIX360/
IBM Watson OpenScale - https://www.ibm.com/cloud/watson-openscale

*Let's Play with Deep Learning!*
Veremin, the Deep Learning Theremin - http://ibm.biz/veremin
magicat, the Command Line image analyzer tool - https://www.npmjs.com/package/magicat
Model Asset eXchange (MAX), ready to use deep learning models - http://ibm.biz/max-models
AI Fairness 360, mitigate unwanted bias from your models - http://aif360.mybluemix.net/data

Transcript

1. Vermont Code Camp 2019
   Intro to Deep Learning
   for Developers
   —
   Maureen McElaney
   Developer Advocate
   Center for Open-Source Data & AI Technologies
   ↳ (CODAIT)
   @Mo_Mack | @ibmcodait | @IBMDeveloper
   medium.com/codait
   github.com/codait | github.com/IBM
   developer.ibm.com
   

   View Slide

2. Is AI overhyped?
   

   View Slide

3. Yes.
   

   View Slide

4. Thank you
   for coming
   to my talk.
   

   View Slide

5. ↳ General Artificial Intelligence
   Metal Skull With Terminator Eye by L.C. Nøttaasen, on Flickr (CC BY-SA 2.0).
   

   View Slide

6. ↳ Broad Artificial Intelligence
   -[ electrIc b88Gal88 ]- by JD Hancock, on Flickr (CC BY 2.0).
   

   View Slide

7. ↳ Narrow Artificial Intelligence
   Danbo on the Lookout by IQRemix, on Flickr (CC BY-SA 2.0).
   

   View Slide

8. Towards Data Science: Cousins of Articifial Intelligence by Seema Singh
   https://towardsdatascience.com/cousins-of-artificial-intelligence-dda4edc27b55
   

   View Slide

9. Applications for Deep
   Learning include (but
   are not limited to...)
   • Image, audio, text classification
   • Object recognition
   • Image caption generation
   • Natural language processing
   • Speech to text conversion
   

   View Slide

10. Software
    Programming
    Untitled by Marcin Wichary, on Flickr (CC BY 2.0).
    

    View Slide

11. 01011001001011000001
    10101101010100100110
    00010110101010011100
    10101010110101010100
    10001001011101000101
    Software Program
    Business Logic
    Input
    Program Execution
    Output
    

    View Slide

12. Input Layer Hidden Layers Output Layer
    

    View Slide

13. View Slide

14. Backpropagation
    Labeled Training Data
    Coat
    Sneaker
    T-shirt Sneaker
    Pullover
    Output Errors
    Pullover
    Coat
    Coat
    Sneaker T-shirt
    ❌
    ❌ ❌
    Fashion-MNIST dataset by Zalando Research, on GitHub (MIT License).
    

    View Slide

15. Input Output
    Sneaker
    98%
    Neural Network Inferencing
    Fashion-MNIST dataset by Zalando Research, on GitHub (MIT License).
    

    View Slide

16. Demo:
    ⬐
    Object identification
    and image segmentation
    with magicat
    
    

    View Slide

17. https://www.npmjs.com/package/magicat
    

    View Slide

18. Install magicat
    $ npm install -g magicat
    + magicat@1.4.9
    added 255 packages from 209 contributors in 11.798s
    

    View Slide

19. Animal photos by Susanne Nilsson, on Flickr (CC BY-SA 2.0).
    23895621638_535be71dee_k.jpg
    37038669284_899d7784a9_k.jpg
    37489697170_31d05aa027_k.jpg
    37699459356_24fd526a5e_k.jpg
    37699976806_5ce694be36_k.jpg
    

    View Slide

20. Scan Directory with magicat
    $ magicat . --contains sheep
    Scanning directory '~/tfjs-demos/magicat' for sheep...
    Sheep found in:
    37038669284_899d7784a9_k.jpg
    37489697170_31d05aa027_k.jpg
    

    View Slide

21. Save Image Segment with magicat
    $ magicat 37699976806_5ce694be36_k.jpg --save horse
    The image '37699976806_5ce694be36_k.jpg' contains the following segments: background, horse.
    saved 37699976806_5ce694be36_k-horse.png
    Animal photos by Susanne Nilsson, on Flickr (CC BY-SA 2.0).
    

    View Slide

22. Demo:
    ⬐
    Veremin, A Video
    Theremin Based
    on PoseNet
    
    

    View Slide

23. “The Octopus Project @ Chop Suey, Seattle, WA, 11/5/2007” by donte, on Flickr
    

    View Slide

24. ↳ http://ibm.biz/veremin
    

    View Slide

25. ↳ Deep Learning Code Patterns
    https://developer.ibm.com/patterns/category/model-asset-exchange/
    

    View Slide

26. Machine
    Learning
    Libraries
    Untitled by Marcin Wichary, on Flickr (CC BY 2.0).
    The Leeds Library by Michael D Beckwith, on Flickr (CC0 1.0).
    

    View Slide

27. View Slide

28. View Slide

29. Applying
    Deep Learning
    Untitled by Marcin Wichary, on Flickr (CC BY 2.0).
    Sharpest tool in the shed by Lachlan Donald, on Flickr (CC BY 2.0).
    

    View Slide

30. Data Science
    Expertise Computing
    Resources
    High-Quality
    Training Data
    Model Deployment
    Time
    Model
    Integration
    Inferencing Code
    And more…
    Sharpest tool in the shed by Lachlan Donald, on Flickr (CC BY 2.0).
    

    View Slide

31. ↳ IBM Developer Model Asset Exchange (MAX)
    https://developer.ibm.com/exchanges/models/
    Classify
    Generate
    Recognize
    

    View Slide

32. Microservice
    Choose deployable model
    Deep Learning asset from the Model Asset Exchange (MAX)
    Deploy
    Swagger specification Inference endpoint Metadata endpoint
    Input preprocessing, model execution, and output post-processing
    Deploy
    model
    Use
    model
    https://developer.ibm.com/exchanges/models/
    

    View Slide

33. AI Lifecycle
    Deploy &
    Run
    Operate
    & Manage
    Prepare,
    Build &
    Train
    ⇄
    ↳ ⬏
    

    View Slide

34. ↳ Preparing, Building, and Training AI Models
    Model Asset Exchange (MAX)
    Data Asset Exchange (DAX)
    

    View Slide

35. ⬏ Deploying and Running AI Models
    ONNX.js
    Model Asset Exchange (MAX)
    

    View Slide

36. ⇄ Operating and Managing AI Systems
    Trusted and Explainable AI
    • AI Fairness 360 Toolkit: Fairness metrics for machine learning models, explanations for
    these metrics, and algorithms to mitigate bias
    • Adversarial Robustness 360 Toolbox: Python library for adversarial attacks and
    defenses for neural networks
    • AI Explainability 360 Toolkit: Interpretability and explainability of data and machine
    learning models
    

    View Slide

37. Resources: Machine Learning Frameworks
    TensorFlow
    https://www.tensorflow.org/
    Train your first neural network: basic classification | TensorFlow
    https://www.tensorflow.org/tutorials/keras/basic_classification
    Keras
    https://keras.io/
    PyTorch
    https://pytorch.org/
    Caffe2
    https://caffe2.ai/
    

    View Slide

38. Resources: IBM Developer
    IBM Developer
    https://developer.ibm.com/
    IBM Cloud
    https://ibm.biz/BdzXfW
    Center for Open-Source Data & AI Technologies (CODAIT)
    http://codait.org/
    IBM Developer Model Asset Exchange (MAX)
    https://developer.ibm.com/exchanges/models/
    Model Asset Exchange (MAX) Code Patterns
    https://developer.ibm.com/patterns/category/model-asset-exchange/
    magicat
    https://github.com/CODAIT/magicat
    Veremin
    https://veremin.mybluemix.net/
    

    View Slide

39. Resources: Preparing, Building, and
    Training AI Models
    Project Jupyter
    https://jupyter.org/
    IBM Developer Model Asset Exchange (MAX)
    https://developer.ibm.com/exchanges/models/
    IBM Watson Knowledge Catalog
    https://www.ibm.com/cloud/watson-knowledge-catalog
    IBM Watson Studio
    https://www.ibm.com/cloud/watson-studio
    

    View Slide

40. Resources: Deploying and Running AI Models
    Data Mining Group (PMML & PFA)
    http://dmg.org/
    ONNX
    https://onnx.ai/
    ONNX.js
    https://github.com/Microsoft/onnxjs
    TensorFlow.js
    https://js.tensorflow.org/
    TensorFlow Lite
    https://www.tensorflow.org/lite
    Core ML
    https://developer.apple.com/machine-learning/
    IBM Watson Machine Learning
    https://www.ibm.com/cloud/machine-learning
    

    View Slide

41. Resources: Operating and Managing AI Systems
    Fabric for Deep Learning (FfDL)
    https://github.com/IBM/FfDL
    AI Fairness 360 Toolkit
    https://github.com/IBM/AIF360
    Adversarial Robustness 360 Toolbox
    https://github.com/IBM/adversarial-robustness-toolbox
    AI Explainability 360 Toolkit
    https://github.com/IBM/AIX360/
    IBM Watson OpenScale
    https://www.ibm.com/cloud/watson-openscale
    

    View Slide

42. What will you
    build with
    deep learning?
    Dynamic Earth - Continental Shelf by NASA Goddard Space Flight Center, on Flickr (CC BY 2.0).
    

    View Slide

43. Thank you.
    Maureen McElaney
    Developer Advocate
    Center for Open-Source Data & AI Technologies
    ↳ (CODAIT)
    —
    @Mo_Mack | @ibmcodait | @IBMDeveloper
    medium.com/codait
    github.com/codait | github.com/IBM
    developer.ibm.com
    

    View Slide

44. View Slide