BayesiaLab 101 Short Course in Mumbai
Core Concepts of Artificial Intelligence with Bayesian Networks
Friday, April 5, 2019, 10:00–17:00 (IST)
Regus, 9th Floor, Platina G Block, Plot C 59, Bandra Kurla Complex, Bandra (East), Mumbai 400 051
Please note that all fees are shown in Singapore Dollars (SGD). As of March 3, 2019, 1 Singapore Dollar (SGD) ≈ 52 Indian Rupees (INR).
BayesiaLab 101 is a new short course introducing you to Artificial Intelligence with Bayesian networks for research, analytics, and reasoning. This course was developed for analysts, scientists, and engineers to help them improve their research workflows by employing Bayesian networks as a practical framework.
- Understand how Bayesian networks fit into the "analytics landscape" of data science, predictive modeling, machine learning, and Artificial Intelligence.
- Learn about the principles of the Bayesian network formalism.
- Practice elementary knowledge modeling and probabilistic inference with Bayesian networks and BayesiaLab.
- Understand the crucial difference between observational inference (prediction) and causal inference (intervention).
- Use BayesiaLab's supervised learning algorithms to create predictive models.
- Experiment with BayesiaLab's unsupervised structural learning algorithms for knowledge discovery and visual exploration in 2D, 3D , and using Virtual Reality.
Course Format, Tools, and Materials
- One-day classroom session, consisting of lectures and practical exercises.
- 60-Day BayesiaLab Education Edition license for classroom use and individual practice.
- Access to all presentation materials, exercises, examples, and datasets for self-study.
- Access to a screen recording of the classroom session.
- BayesiaLab 101 Certificate of Achievement upon course completion.
Classroom Session Agenda
Part 1 (Approx. 2 Hours)
- The Promise, the Peril, and the Limitations of Artificial Intelligence
- Human Cognitive Limitations & Biases in Reasoning
- Dimensions of Reasoning: A Conceptual Map of Analytic Modeling and Reasoning
- Inference Type: Probabilistic vs. Deterministic
- The Limitations of Logic
- Bayes' Rule for Probabilistic Inference
- Model Purpose: Observational vs. Causal Inference
- Model Source: Data vs. Theory
- Inference Type: Probabilistic vs. Deterministic
- Proposing Bayesian Networks as a Reasoning Framework
- The Bayesian Network Formalism
- Directed Acyclic Graphs & Their Properties
- Introductory Example: Medical Expert System
- Joint Probability Distributions
- Probability Calculus & Factorization
- Properties Benefits of Bayesian Networks
Part 2 (Approx. 4 Hours)
The sequence of examples in Part 2 mirrors the quadrants in the proposed Map of Analytic Modeling and Reasoning:
- Knowledge Encoding & Diagnosis
- Knowledge Modeling with Domain Expertise
- Probabilistic Reasoning
- Reasoning in Court
- Where is My Bag?
- Knowledge Discovery & Classification/Prediction
- Machine Learning with BayesiaLab
- Data Import
- Data Discretization
- Learning = Searching
- MDL Score
- Supervised Learning
- Wisconsin Breast Cancer Database
- Coronary Artery Disease Diagnosis
- Machine Learning with BayesiaLab
- Knowledge Discovery & Interpretation
- Unsupervised Structural Learning
- Visual Analysis in 2D and 3D
- Analysis of Exchange-Traded Funds
- Causal Inference
- Simpson’s Paradox
- Encoding Causal Assumptions
- Performing Causal Inference
- Determining Advertising Effectiveness
BayesiaLab 101 Short Course Registration
Please note that all fees are shown in Singapore Dollars (SGD).
- BayesiaLab 101 Online Forum Launch: March 15, 2019
- BayesiaLab Education License Period: March 25 through May 24, 2019
- One-Day Classroom Session in Mumbai: Friday, April 5, 2019
- Final Quiz (Administered Online on Demand): available May 18–24, 2019
BayesiaLab Education Edition
During the BayesiaLab 101 course, you will use the Education Edition of BayesiaLab 8 on your own computer. The Education Edition is functionally equivalent to the full commercial edition of BayesiaLab Professional, with the following exceptions:
- The number of variables/nodes is limited to 50.
- The maximum size of a dataset for learning is 1,000 rows/records.
Who should join the course?
If you are working in any of the following fields, our course will demonstrate the practical relevance of Bayesian networks for research and analytics:
Applied Research • Biotechnology • Data Science • Decision Analysis • Ecology • Economics • Econometrics • Engineering • Epidemiology • FinTech • Intelligence Analysis • Marketing Science • Machine Learning • Medical Research • Operations Research • Policy Analysis • Quant Research • Risk Management • Social Science • Strategic Planning
While computer scientists are welcome to join the course, please note that the discussion of algorithms and program code is out of scope.
What's required to register?
- There is no formal educational requirement, although most participants typically have a bachelor's or master's degree.
- Basic data manipulation skills, e.g., handling tabular data with Excel.
- Familiarity with basic statistical techniques, such as regressions.
- No prior knowledge of Bayesian networks is required.
- No programming/coding skills are required. You will exclusively use the graphical user interface of BayesiaLab for all exercises.
- For a general overview of Bayesian networks, we suggest that you download a free copy of our book, Bayesian Networks & BayesiaLab. Although by no means mandatory, reading its first three chapters would be an excellent preparation for the course.
What to prepare for the classroom session?
- Program participants need to download and install BayesiaLab on a WiFi-enabled laptop/notebook with a Windows or Mac operating system prior to the start of the classroom session.
- Technical support for the BayesiaLab installation is available during the week prior to the classroom session, but not on the day of the classroom session. All technical issues need to be resolved beforehand.
- A Linux version of BayesiaLab is also available for download, but there will be no technical/installation support to those who choose to install it.
- Participants must bring their own computer to the classroom session. Using a mouse as a pointing device is highly recommended.
Classroom Session Miscellanea
- Please feel free to dress comfortably, but bear in mind that our classroom is in an office environment.
- A complimentary lunch will be served around 12 noon.
- Coffee and tea will be available throughout the day.
About the Instructor
Stefan Conrady has over 20 years of experience in analytics, marketing, and strategic planning with leading automotive brands, such as Mercedes-Benz, BMW, and Rolls-Royce Motor Cars. Stefan is a native of Ulm, Germany, but his career has spanned the globe, having lived and worked in Chicago, New York, Munich, and Singapore, just to name a few. In his most recent corporate assignment, he was heading the Analytics & Forecasting group at Nissan North America.
Today, in his role as Managing Partner of Bayesia USA and Bayesia Singapore, he is recognized as a thought leader in applying Artificial Intelligence for research, analytics, and reasoning. Stefan's tutorials, seminars, and lectures on Bayesian Networks are widely followed by scientists who embrace AI innovations to accelerate applied research. In this context, Stefan has recently co-authored a book with Lionel Jouffe, Bayesian Networks & BayesiaLab — A Practical Introduction for Researchers.
Terms & Conditions
- Course cancellations by participants will be refunded in full up to 7 days prior to the classroom session.
- Within 7 days prior to the classroom session, cancellations by participants will not be refunded but can be applied to future training programs or BayesiaLab software products (prevailing list prices apply).
- On or after the date of the classroom session, refunds or credits will no longer be issued.
- Bayesia reserves the right to cancel the course prior to the date of the classroom session for any reason.
- In the event of the cancellation of the course by Bayesia, all fees will be refunded to the participants in full within three days.
- The BayesiaLab Education license is not renewable beyond the 60-day course period.
- Bayesia is not responsible for any expenses the participants incur in the context of the course or in the event of its cancellation.
- All travel expenses in conjunction with the course are the participant's own responsibility.
- The BayesiaLab software is licensed by Bayesia S.A.S.
- All course fees are invoiced and charged by Bayesia Singapore Pte. Ltd. in Singapore Dollars.
- The one-day classroom session is provided on a complimentary basis with the purchase of the course package, which includes the 60-day BayesiaLab Education Edition license, online training materials, access to the online forum, and a BayesiaLab 101 Certificate.
- All materials related to the course are produced, copyrighted, and hosted by Bayesia USA. They are delivered electronically to course participants via Bayesia Singapore Pte. Ltd.
- No course participant shall copy, distribute, or resell the course materials without the explicit written permission from Bayesia USA and/or Bayesia Singapore Pte. Ltd.
How does BayesiaLab 101 compare to the Professional BayesiaLab Courses?
BayesiaLab 101 is also an excellent preparation—but not a requirement—for the more comprehensive Professional BayesiaLab Courses that we offer on a regular basis around the world (see comparison chart below). Compared to the three-day courses, BayesiaLab 101 provides a shorter and more streamlined introduction but does not take any shortcuts. Given the smaller classroom component with BayesiaLab 101, we are able to offer this new course at a more accessible price point.
Please feel free to email us: email@example.com