Introduction to ML.NET
Download as PPTX, PDF1 like273 views
The document discusses advancements in artificial intelligence and machine learning, emphasizing the growing importance of conversational agents and text analytics. It highlights the evolution of machine learning from theoretical foundations to practical applications powered by modern computing capabilities. The text also illustrates various machine learning concepts, including regression, classification, anomaly detection, and automated model building tools.
![Text Featurizer
Featurized Text
[0.76, 0.65, 0.44, …]
[0.98, 0.43, 0.54, …]
[0.35, 0.73, 0.46, …]
[0.39, 0, 0.75, …]
Example
Text
Wow... Loved this place.
Crust is not good.
Not tasty and the texture was just nasty.
The selection on the menu was great.
2. Transformers](https://image.slidesharecdn.com/2019-190906071545/85/Introduction-to-ML-NET-13-320.jpg)
Introduction to ML.NET
- 3. Artificial Intelligence • Conversational Agents • Text Analytics Machine Learning • Regression • Classification • Anomaly Detection Deep Learning • Neural Networks • Computer Vision
- 4. Why now and not before? • Theory since ’50s/’60s/’70s • Obstacles • Strong math skills • Continuous training • Now • computing power • Commodity and Cloud • Discipline (components, API, microservices) • Everyone asks
- 5. Everyone is a Data Scientist «The italian way »
- 6. Two roles • Who create (and train) the model (the new «component» market) • Who consume the model
- 7. Something really happened (a week ago) • Example IoT scenario • (another example of «why now») • Solution in Python • Python has won • .NET (Core) Crysis • Spikes handled with thresholds (and hysteresys) • Work on levels • Failure on this solution • Thresholds changes, slope not • I said «why don’t you use scikit learn»? • Answer: «Too difficult»
- 8. Difficulties of «modern» ML • Derivatives/gradients • Limits • Series • Distributions “It has exquisite buttons … with long sleeves …works for casual as well as business settings” f(x) f(x)
- 9. ML.NET 1.0 • Machine Learning framework for building custom ML Models • Custom ML made easy - Automated ML and Tools (Model Builder and CLI) • Proven at scale (Azure, Office, Windows ) • Extensible (TensorFlow, ONNX and Infer.NET) • Cross-platform and open-source - Runs everywhere
- 12. Example Comment Text Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 1 1. Data
- 13. Text Featurizer Featurized Text [0.76, 0.65, 0.44, …] [0.98, 0.43, 0.54, …] [0.35, 0.73, 0.46, …] [0.39, 0, 0.75, …] Example Text Wow... Loved this place. Crust is not good. Not tasty and the texture was just nasty. The selection on the menu was great. 2. Transformers
- 14. Example Estimator Comment Sentiment Wow... Loved this place. 1 Crust is not good. 0 Not tasty and the texture was just nasty. 0 The selection on the menu was great. 0 3. Estimators
- 15. Regression Infer future values (interpolation?) from the past Classification When the data are being used to predict a category When there are only two choices, it's called binary classification. When there are more categories it is called multi-class classification. Anomaly Detection identify data points that are simply unusual
- 17. Regression Trees • A decision (or regression) tree is a binary tree-like flow chart, where at each interior node one decides which of the two child nodes to continue to based on one of the feature values from the input.
- 19. Object Detection
- 20. ONNX Runtime
- 24. Mileage Condition Car brand Year of make Regulations … Parameter 1 Parameter 2 Parameter 3 Parameter 4 … Gradient Boosted Nearest Neighbors SVM Bayesian Regression LGBM … Mileage Gradient Boosted Criterion Loss Min Samples Split Min Samples Leaf Others Model Which algorithm? Which parameters?Which features? Car brand Year of make
- 25. Criterion Loss Min Samples Split Min Samples Leaf Others N Neighbors Weights Metric P Others Which algorithm? Which parameters?Which features? Mileage Condition Car brand Year of make Regulations … Gradient Boosted Nearest Neighbors SVM Bayesian Regression LGBM … Nearest Neighbors Model Iterate Gradient BoostedMileage Car brand Year of make Car brand Year of make Condition
- 26. Which algorithm? Which parameters?Which features? Iterate
- 27. Enter data Define goals Apply constraints OutputInput Intelligently test multiple models in parallel Optimized model
- 28. Automated ML Capabilities • Based on Microsoft Research • Brain trained with several million experiments • Collaborative filtering and Bayesian optimization • Privacy preserving: No need to “see” the data
Editor's Notes
- #11: 10
- #13: Dataset: https://github.com/dotnet/machinelearning/blob/master/test/data/wikipedia-detox-250-line-data.tsv
- #14: Transformers take data, do some work on it, and return new transformed data. One example of a transformer we will need in our example is a Text Featurizer, which takes the text in the issue text and converts it to numbers that our ML algorithms can understand.
- #15: An estimator learns from data to create a transformer. Now a model, which turns the input features into output predictions, is a transformer. So we can take estimators that take our example data and produce a model.