2. Tutorials

2.1. Functional programming

Collection for concept and practice for Python in functional programming.

• 2.1.1. Scripting via function
  • 2.1.1.1. Featured syntax
  • 2.1.1.2. Unit of data processing
• 2.1.2. Pipelining data process
  • 2.1.2.1. Normalized scientific computing
  • 2.1.2.2. Automation experiment
  • 2.1.2.3. Automation testing

2.2. Data access and processing

This collection of tutorials provides foundational guidance on managing, transforming, and preparing data for biomedical and imaging workflows. Topics include efficient data inflow strategies, format conversion techniques, specialized handling of DICOM metadata, and practical methods for data augmentation to enhance dataset utility. Explore these guides to streamline data workflows, ensure compatibility across tools, and optimize inputs for downstream analysis or machine learning applications.

• 2.2.1. Preparing batch processing
  • 2.2.1.1. Applying generator function
  • 2.2.1.2. File searcher and folder relocation
  • 2.2.1.3. Universal data loader
• 2.2.2. Transform and identification
  • 2.2.2.1. Edge and corner detection
  • 2.2.2.2. Segmentation for quantitative statistics
  • 2.2.2.3. Data processing on different disciplines
• 2.2.3. DICOM related operations
  • 2.2.3.1. Regroup DICOM dataset
  • 2.2.3.2. Construct DICOM images
  • 2.2.3.3. Comprehensive applications
• 2.2.4. Applying data augmentation
  • 2.2.4.1. Determine appropriate transformation
  • 2.2.4.2. Random observer on data

2.3. Edge devices and self-adaption AI

These tutorials explore how intelligent edge systems unify streaming data, edge computing, and adaptive machine learning to enable self-improving AI in resource-constrained environments. Learn to process raw data streams locally into real-time insights—eliminating cloud dependency—while addressing hardware limits, dynamic data shifts, and privacy risks. Through real-world examples, explore systems where AI models improve themselves using live data—without sacrificing speed, precision, or edge-device performance.

• 2.3.1. From streaming data to edge AI
  • 2.3.1.1. Edge computing on data stream
  • 2.3.1.2. Incremental online learning and edge AI
  • 2.3.1.3. Edge intelligence implementation strategies
• 2.3.2. Adaptive AI with online learning
  • 2.3.2.1. Redefining intelligence via adaptive models
  • 2.3.2.2. Self evolving meta models and demonstrations

---

Authors:

Chen Zhang

Version:

0.0.5

Created on:

Jan 2, 2024