Subjects
Technology
3D AI Algorithms Artificial Intelligence Big Data Blockchain Computer Networking Computer Science Computer Security Computer Vision Cryptography Cyber Security Data Analysis Data Mining Data Science Deep Learning Machine Learning Neural Networks Programming Software Engineering Web Development
Science
Anatomy Astrobiology Astronomy Biochemistry Biology Chemistry Epidemiology Genetics Geology Neuroscience Physics Physiology
Business
Accounting Business Development Business Strategy Economics Entrepreneurship Finance Marketing Operations Management Project Management
Humanities
Ancient History Anthropology Art History Ethics Gender Studies History Literature Philosophy Psychology Sociology
Health & Medicine
Clinical Trials Health Education Healthcare Nursing Nutrition Public Health
Law
Contract Law Corporate Law International Law Labor Law
Education
Curriculum Development E-Learning Educational Technology Higher Education Instructional Design Special Education
Arts & Design
Architecture Art & Design Fashion Design Graphic Design Interior Design UX/UI Design
Other
Environmental Science Ethnic Studies Music Theory Political Science Religious Studies

Conversational Virtual Assistants with Deep Learning

While commercial virtual assistants today can perform over hundreds of thousands of skills, they require a tremendous amount of manual labor. This course focuses on the latest virtual assistant research that uses deep learning to lower the development cost, improve the scalability and robustness, and to add dialogue capabilities to enhance the user experience. Students will learn both the theory and practice with written and programming assignments, as well as a course project of their own design. 

Topics Include

  • A virtual assistant architecture that uses deep learning to
    • Semantically parse dialogues to the ThingTalk virtual assistant programming language
    • Generate responses
    • Recover from parsing errors through user feedback
  • Neural dialogue semantic parser generators from high-level specifications such as database schemas and API signatures
  • Robust, sample-efficient training for dialogues by combining few-shot data with synthesized data
  • Multilingual, mixed-initiative, multimodal assistants; federated privacy-protecting assistants
Course Page
Price
$5,600.00 Subject to change
Delivery
Online, instructor-led
Level
Advanced
Commitment
10 weeks, 10-20 hrs/week
School
Stanford School of Engineering
Language
English