End to end machine learning with DataRobot AI Cloud Platform
DataRobot AI Cloud is a new approach built for the demands, challenges and opportunities of AI today. It’s a a single system of record, accelerating the delivery of AI to production for every organization. All users collaborate in a unified environment built for continuous optimization across the entire AI lifecycle.
It is designed for the collaboration for all users in enterprise:
- Data Science & Analytics Experts
- IT & DevOps Teams
- Executives & Information Workers
The AI Platform has 3 main functionalities:
1. Data Preparation (Make your data ready for machine learning)
2. Machine Learning (AutoML, VisualML)
3. MLOps (Deploy your model per your need)
In this tutorial we are focussing on the second part of AI platform “Machine Learning”. We are going to cover in-depth details about model building process and explain most of the functionalities related to AI cloud model training, evaluation, performance, re-training, validation and various other steps.
Content:
- AI cloud platform access
- Data Preparation Tutorial Intro
- ML Development Project
- Importing Dataset for ML
- ML Focussed EDA with source data
- Supervised ML with AI Platform
- Advance Options with ML Training
- ML Training Start
- Data Quality Exploration
- Features List in Source Data
- Features Association
- Data Quality Assessment
- AI Models in ML Project
- AI Models Repo
- Bias and Fairness
- Feature Impact and Feature Effect
- Prediction Explanations
- Explore Model Details
- Model Evaluations
- Advance Model Tuning
- Model comparisons
- Model Speed vs Model Accuracy
- Model Insight
- Improving Model Accuracy
- Ensembling or Model Blending
- Deploy Model from ML Pipeline
- AI Report Generation
- AI Platform Documentation
Thank you, Be Good and Do Good.
