![17
[glacier]
17
Google Photos](https://image.slidesharecdn.com/mlwithtensorflow-181114122410/85/Machine-learning-with-TensorFlow-17-320.jpg)
Machine learning with TensorFlow
- 2. Eslam saeed ➔ Web developer at Savvy Tech. ➔ Freelancer as a web developer since 2015. ➔ GDG Alexandria Co-Organizer ➔ Founder at HYPEREM 2 Eslamsa3ed50@gmail.com
- 3. 3 Modern Machine Intelligence Real World Impact Introduction to Machine Learning Moving onto MLCC What’s TensorFlow Our Agenda You should be excited about what’s coming! 😆
- 4. 4
- 6. “Modern Machine Intelligence is a branch of computer science that builds systems to perform similar functions to human intelligence, such as learning, reasoning, self-correcting, and adapting. 6 Modern Machine Intelligence
- 7. 7 Real World Impact 5- Real-world 4- Google products ML has already made a huge impact in the world especially in the areas of science and health care.
- 8. 8
- 9. 9 Image of retina Blood pressure predictions focus on blood vessels Person’s risk of a heart attack or stroke
- 13. 13 Machine Learning is Widely Used at Google
- 14. A mobile-first product ● Optimized for the small screen ● Optimized for touch interfaces ● Near-ubiquitous connectivity ● Low power An AI-first product ● Learns and adapts ● Assists and anticipates ● Conversational and interactive ● Context aware ● Trustworthy
- 16. 16 Street nameStreet number Street View Sign Business facade Sign Business name Traffic light Traffic signStreet number
- 18. 18 Smart reply in Gmail 10% of all responses sent on mobile
- 19. “ What’s Machine Learning ? 19 ML is the process of training a piece of software, called a model, to make useful predictions using a data set. This predictive model can then serve up predictions about previously unseen data.
- 20. 20 Define a ML problem and propose a solution Construct your dataset Transform data Use the model to make predictions Train a model Idea to Implementation
- 21. ML Use Cases Structured Data Classification/ Regression ● Customer Churn Analysis ● Product Diagnostics ● Forecasting Recommendation ● Content Personalization ● Product X-Sells/Up-sells Anomaly Detection ● Fraud Detection ● Asset Sensor Diagnostics ● Log Metric Anomalies Unstructured Data Image Analytics ● Identify damaged shipments ● Explicit Content Classification ● Identify “styles” in images Text Analytics ● Call Center log analysis ● Language Identification ● Topic Classification ● Sentiment Analysis
- 22. blog.tensorflow.org youtube.com/tensorflow Launching new resources for learning and sharing 22
- 23. A repository of pre-trained model components, packaged for one-line reuse Easiest way to share and use best approaches for your task tensorflow.org/hub 23
- 25. Questions ? Do you’ve any question 25
- 26. THANKS! Any questions? You can find me at @eslamsa3ed11 & eslamsa3ed@yahoo.com 26
- 28. CREDITS Special thanks to all the people who made and released these awesome resources : ▸ Theme by SlidesCarnival ▸ Photographs by Death to the Stock Photo (license) 28 Shapes & icons © 2018 Google Inc, used with permission. Google and the Google logo are registered trademarks of Google Inc. Google Drive® is a registered trademark of Google Inc. Trademarks