Machine Learning for .NET Developers - ADC21

Machine Learning for .NET Developers - ADC21

• 1.
  Machine Learning for.NET Developers Gülden Bilgütay @gubilgu
• 2.
  A few pointsabout ML concepts to know as a .NET developer…
• 3.
  Machine Learning Typical E2EProcess … Prepare Experiment Deploy Orchestrate
• 4.
  Complexity of MachineLearning Source: http://scikit-learn.org/stable/tutorial/machine_learning_map/index.html - Mean Absolute Error (MAE) - Root of mean squared Error (RMSE) - Area under the curve (AUC) - Loss function - Log loss - Accuracy - Precision - Recall - F-score - Hyperparameters - # of nodes - # of trees - Weights of nodes …etc. …. …… ……… Evaluation Metrics
• 7.
  AutoML 1.Identify the MLproblem to be solved: classification, forecasting, regression…etc. 2.Specify the source and format of the labeled training data: 3.Configure the compute target for model training 4.Configure the automated machine learning parameters 5.Submit the training run. 6.Review the results
• 8.
   Open-source proxybetween .NET and ML community  Automatic predictions using the data available to your application
• 9.
  Who is usingML.NET?  At Microsoft:  Outlook, M365, O365, Microsoft Defender, Azure AutoML, Power BI...  For other real use cases, check out: ML.NET Customer Showcase ML.NET in the Real World @ .NET Conf
• 10.
  Resources http://dot.net/ml http://aka.ms/mlnetsamples http://aka.ms/mlnetdocs http://aka.ms/mlnet https://aka.ms/mlnetyoutube http://aka.ms/mlnet-workshop
• 11.
  • Collect andload training data into an IDataView object • Specify a pipeline of operations to extract features and apply a machine learning algorithm • Train a model by calling Fit() on the pipeline • Evaluate the model and iterate to improve • Save the model into binary format, for use in an application • Load the model back into an ITransformer object • Make predictions by calling CreatePredictionEngine.Predict()
• 12.
  Model Portability -ONNX Use your favorite deep learning frameworks without getting locked into one framework ONNX Community project created by Facebook and Microsoft Use the best tool for the job. Train in one framework and transfer to another for inference TensorFlow PyTorch Scikit-Learn MXNet Chainer Keras
• 13.
  Let’s Demo -Hands-On
• 15.
  PROs & CONs
• 16.
  E2E scenarios
• 17.
  Edge deployment
• 18.
  https://docs.microsoft.com/en- us/azure/architecture/reference- architectures/ai/end-to-end-smart-factory
• 19.
  https://docs.microsoft.com/en-us/azure/architecture/reference-architectures/ai/mlops-python
• 20.
  © Copyright MicrosoftCorporation. All rights reserved. Q&A – Thank you ! https://github.com/gldnblgty/ADC21_HandsOnDemo