Machine Learning with Tensorflow - I/O extended 2018

Transcript

2. Getting started with ML using Tensorflow’s high-level APIs Akash Tandon Data Engineering @ SocialCops
3. XKCD comics
4. Moving beyond the buzzwords Onalytica.com
5. Machine learning in a nutshell - What is ML? - What exactly is a model again? - Types of ML algorithms - When to use it?
6. Machine learning in a nutshell "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.” - Tom Mitchell
7. ML programming model Source
8. ML in the wild - Health industry - Agriculture - E-commerce - .. and the list goes on!
9. 7 steps of ML - Gathering data - Data preparation - Choosing a model - Training - Evaluation - Parameter tuning - Prediction We’ll better understand these steps through a code example further ahead.
10. Why Tensorflow? - History - Concept of graphs - Support of end-to-end workflow including deployment - Vibrant community and diverse ecosystem including support for multiple languages including Python, JS, and R
11. What’s with the name? - Tensor + Flow - Tensors - Graphs and dataflow
12. Tensors ~ data representation source
13. Dataflow graphs source
14. Hello world of ML - Image classification using MNIST dataset - We’ll use Google’s CoLab for this.
15. Time to code!
16. I built my model, but what now?
17. Enter Tensorflow serving - Flexible, high-performance serving system for machine learning models, designed for production environments. - Export your pre-trained model and serve them to consumers/customers.
18. Diverse ecosystem - Move across languages and re-use your models - Train your model in R or Python - Serve them in production using Javascript using tensorflow.js - Visualize processes using Tensorboard - Serve models using tf-serving - Make music and art using Tensorflow Magenta - … and a lot more!
19. ML resources - https://ai.google/education/ - https://developers.google.com/machine-learning/crash-c ourse/ - https://github.com/tensorflow/workshops - https://www.coursera.org/learn/machine-learning
20. Email: akash@socialcops.com Twitter: @AkashTandon Github: @analyticalmonk Feel free to reach out
21. That’s all, folks!