Slide 1

Slide 1 text

A Gentle Introduction to Deep Learning for Developers — Bradley Holt Program Manager, Developer Advocacy Center for Open-Source Data & AI Technologies ↳ (CODAIT) @BradleyHolt | @ibmcodait | @IBMDeveloper medium.com/codait github.com/codait | github.com/IBM developer.ibm.com

Slide 2

Slide 2 text

Is AI overhyped? Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 3

Slide 3 text

Yes Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 4

Slide 4 text

Thank you for coming to my talk Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 5

Slide 5 text

↳ General Artificial Intelligence Metal Skull With Terminator Eye by L.C. Nøttaasen, on Flickr (CC BY-SA 2.0). Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 6

Slide 6 text

↳ Broad Artificial Intelligence -[ electrIc b88Gal88 ]- by JD Hancock, on Flickr (CC BY 2.0). Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 7

Slide 7 text

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

Slide 8

Slide 8 text

Approaches to Artificial Intelligence Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Machine Learning • Predictive analytics • Data mining • Anomaly detection • Email filtering Deep Learning • Image or audio classification • Facial recognition • Object recognition • Image caption generation • Natural language processing

Slide 9

Slide 9 text

Demo: ⬐ Object identification and image segmentation with magicat Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 10

Slide 10 text

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

Slide 11

Slide 11 text

Install magicat $ npm install -g magicat + [email protected] added 255 packages from 209 contributors in 11.798s

Slide 12

Slide 12 text

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

Slide 13

Slide 13 text

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

Slide 14

Slide 14 text

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).

Slide 15

Slide 15 text

Demo: ⬐ Veremin, A Video Theremin Based on PoseNet Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 16

Slide 16 text

Untitled by Ash Nowak, on Flickr (CC BY-SA 2.0).

Slide 17

Slide 17 text

↳ https://veremin.mybluemix.net/

Slide 18

Slide 18 text

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

Slide 19

Slide 19 text

Software Programming Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Untitled by Marcin Wichary, on Flickr (CC BY 2.0).

Slide 20

Slide 20 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation 01011001001011000001 10101101010100100110 00010110101010011100 10101010110101010100 10001001011101000101 Software Program Business Logic

Slide 21

Slide 21 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation 01011001001011000001 10101101010100100110 00010110101010011100 10101010110101010100 10001001011101000101 Software Program Input Program Execution Output

Slide 22

Slide 22 text

Machine Learning vs. Software Programming Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Machine Learning • Training • High-quality examples (i.e., training data) • Approximation of a correct function Software Programming • Programming • Set of direct instructions • Precisely-defined function

Slide 23

Slide 23 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Input Layer Hidden Layers Output Layer

Slide 24

Slide 24 text

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).

Slide 25

Slide 25 text

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

Slide 26

Slide 26 text

Machine Learning Libraries Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Untitled by Marcin Wichary, on Flickr (CC BY 2.0). The Leeds Library by Michael D Beckwith, on Flickr (CC0 1.0).

Slide 27

Slide 27 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation

Slide 28

Slide 28 text

No content

Slide 29

Slide 29 text

Applying Deep Learning Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Untitled by Marcin Wichary, on Flickr (CC BY 2.0). Sharpest tool in the shed by Lachlan Donald, on Flickr (CC BY 2.0).

Slide 30

Slide 30 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation 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).

Slide 31

Slide 31 text

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

Slide 32

Slide 32 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation 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/

Slide 33

Slide 33 text

AI Lifecycle Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Deploy & Run Operate & Manage Prepare, Build & Train ⇄ ↳ ⬏

Slide 34

Slide 34 text

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

Slide 35

Slide 35 text

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

Slide 36

Slide 36 text

⇄ Operating and Managing AI Systems Fabric for Deep Learning (FfDL) Train and deploy deep learning models on Kubernetes using TensorFlow, Caffe2, PyTorch, and other frameworks Trusted 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

Slide 37

Slide 37 text

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

Slide 38

Slide 38 text

Resources: Machine Learning Libraries 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/

Slide 39

Slide 39 text

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/

Slide 40

Slide 40 text

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

Slide 41

Slide 41 text

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

Slide 42

Slide 42 text

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

Slide 43

Slide 43 text

Thank you. Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation Bradley Holt Program Manager, Developer Advocacy Center for Open-Source Data & AI Technologies ↳ (CODAIT) — @BradleyHolt | @ibmcodait | @IBMDeveloper medium.com/codait github.com/codait | github.com/IBM developer.ibm.com

Slide 44

Slide 44 text

Center for Open-Source Data & AI Technologies (CODAIT) / August 21, 2019 / © 2019 IBM Corporation