This class starts with a general overview of AI, neural network architecture, and deep learning. Medical image classification and segmentation will be introduced with examples of multi-spectral endoscopic narrowband imaging data classification. The class covers computer vision, image understanding, natural language understanding, such as sentence classification, keyword extraction, and automatic medical report generation, and build a domain-specific speech recognition model using custom language models. This class will provide a hands-on project to build a specialized AI for paramedics procedures.

Schedule: Every Wednesday at 5-7 pm PST starting Nov. 18 to Dec. 9
Location: Zoom

Learning Outcomes

Check Mark Gain experience in learning basic AI architecture

Check Mark Knowledge of building digital “eyes” and “ears” for AI systems

Check Mark Learn to create specialized AI systems for specific applications.

Our Instructors

Dr.Thomas Lu

Dr. Thomas Lu

Senior Researcher at NASA Jet Propulsion Lab (JPL)

Dr. Lu has been doing research in the forefront of science and technologies. His research focus has been in data analysis, artificial intelligence (AI), neural network architecture, deep learning and computer vision areas. He has served as an organizer and organizing committee member of SPIE conferences, edited a book on “Advancement in Patten Recognition Research”, contributed 3 book chapters, co-authored over 70 journal and conference papers, co-invented 6 patents.

Dr.Kyongisk Yun

Dr. Kyongisk Yun

Technologist at NASA Jet Propulsion Lab (JPL)

His research focuses on building brain-inspired technologies and systems, including deep learning computer vision, natural language processing, and brain-computer interfaces. He received JPL Explorer Award (2019) for scientific and technical excellence in machine learning applications.


There is an explosion of AI research and applications. The lecturers have been doing AI research for many years. They created specialized AI assistants for firefighters, hazmat teams and paramedics. Healthcare is the perfect place to apply AI technologies. This class provides hands on experience in learning the state-of-the-art AI, deep learning and applications for image analysis and speech understanding. This class will provide you with the opportunity to learn how to design and create highly intelligent AI systems that integrate multiple technologies to interact with humans and enable health professionals to perform everyday tasks.

Target Audience

Data scientists, computer scientists, healthcare researchers and engineers, R&D managers, and hobbyist in big data analysis, AI, image analysis, speech processing, human computer interfaces.

RMDS Training Program Design

Creation of Specialized AI Assistant for Healthcare Industry

Course Structures
(By the end of this lesson, you should be able to answer the following questions)
1 General introduction to healthcare AI
Neural network architecture and training overview
Principles of neural network learning and optimization in various applications
2 Diagnosis: Disease diagnosis using big data and deep learning
Physiological and sociodemographic data analysis for disease diagnosis Build a customized ChatBot
Hyperparameter tuning, architecture search
3 Reporting: Natural language understanding (sentence classification, keywords extraction, automatic medical report generation)
Build a domain specific speech recognition using custom language mode
Natural language processing, sequence models (LSTM, GRU)
4 Medical Imaging: Medical image classification and segmentation
Example in multi-spectral endoscopic narrowband imaging data classification
Multi-spectral image processing, deep learning
Object recognition and segmentation