.svg)
SPOC
Applying Machine Learning to Engineering and Science
Learning Platform
MIT xPRO Learning Platform
Location
Duration
6 weeks
Time Commitment
.svg)
Learning Platform
MIT xPRO Learning Platform
Location
Duration
6 weeks
Upcoming Sessions
Jan 1, 2026
-
Dec 1, 2026
Outcomes
Learning Outcomes
Feature Engineering for data preparation and model accuracy.
Application of Predictive Analytics to real-world problems.
Use of Neural Networks for image and seismic data processing.
Mastery of Linear Regression for oil and gas production.
Understanding Geometric Data processing techniques.
Implementing Risk Quantification in complex systems.
Applying Bayesian Approaches to aerospace challenges.
Optimization of Surrogate Models in simulations.
Exploring Dimensionality Reduction techniques in ML.
Use of Active Learning for optimal experimental design.
You Will Get
Official Certificate From MIT
.avif)
Live Interactive Sessions
Modules
Feature Engineering in Li-Ion Battery Life Prediction
Learners will apply feature engineering techniques to predict battery life.
- Learn about feature identification and regularization techniques.
- Understand the role of feature engineering in predicting battery lifespan.
- Complete a graded assignment on feature engineering application.
Machine Learning for Computational Imaging
Learners will utilize machine learning to solve imaging problems.
- Explore inverse problems and phase retrieval techniques.
- Learn neural networks for image synthesis and tomography.
- Engage in a graded assignment on computational imaging.
Seismic Deepfakes – Neural Nets to Generate Missing Data
Learners will use neural networks to handle missing data in seismic applications.
- Study seismic waves and wave equations.
- Implement neural networks for seismic data recovery.
- Complete a graded assignment on seismic deepfakes.
Prediction of Oil and Gas Production
Learners will predict future oil and gas production using machine learning.
- Learn linear regression techniques for energy production data.
- Analyze and predict future production rates with machine learning models.
- Participate in a graded assignment on oil production prediction.
Machine Learning in Geometric Representations
Learners will apply machine learning to geometric data and 3D point clouds.
- Understand geometric data processing using machine learning.
- Work on point cloud and vector data analysis.
- Engage in a graded assignment focusing on 3D geometric learning.
Quantifying Risk in Complex Systems Using Machine Learning
Learners will use machine learning to assess risk in complex systems.
- Study probabilistic approaches to extreme events.
- Learn about active learning and experimental design for risk quantification.
- Complete a graded assignment on risk modeling.
Machine Learning for Accelerating Computational Materials Discovery
Learners will accelerate materials discovery with machine learning.
- Analyze inorganic chemistry data with machine learning models.
- Explore feature selection and uncertainty quantification techniques.
- Engage in a graded assignment on materials discovery.
Practical Machine Learning in Composite Design
Learners will use machine learning for designing advanced materials.
- Learn materials science fundamentals and apply machine learning to materials design.
- Use ML for image classification and fracture propagation prediction.
- Complete a graded assignment on composite material design.
Machine Learning in Aerospace
Learners will apply machine learning to solve aerospace challenges.
- Explore inverse problems and Bayesian approaches in aerospace.
- Learn dimensionality reduction and surrogate modeling techniques.
- Participate in a graded assignment on aerospace applications.
Academic Team
Youssef M. Marzouk
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Director of the MIT Center of Computational Engineering, Associate Professor of Aeronautics, and Director of the Aerospace Computational Design Laboratory at MIT He is also a core member of MIT's Statistics and Data Science Center His research interests include computational mathematics, uncertainty quantification, inverse problems, data assimilation, and Bayesian statistics.
.avif)
Heather Kulik
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Associate Professor of Chemical Engineering at MIT Her research interests include computational chemistry, transition metal chemistry, molecular design, density function theory, and enzyme catalysis
Richard Braatz
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Professor of Chemical Engineering at MIT His research interests include systems theory, systems and control theory, fault diagnosis, manufacturing processes, and manufacturing systems.
George Barbastathis
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Professor of Mechanical Engineering at MIT His research interests include optics, computational imaging, machine learning, and inverse problems. Former research includes creation of a macroscopic invisibility cloak for visible light
Themistoklis Sapsis
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Associate Professor of Mechanical and Ocean Engineering at MIT His research interests include uncertainty quantification, data science, extreme events, fluid dynamics, and ocean engineering.
Justin Solomon
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Associate Professor of Electrical Engineering and Computer Science at MIT His research interests include computer graphics, geometry processing, and machine learning.
John Williams
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Professor of Civil and Environmental Engineering at MIT His research interests include information technology, cyber/physical security, web-based education technology, large scale network simulation, and geonumerics of granular and powder systems.
Markus Buehler
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Professor of Engineering and Head of the Department of Civil and Environmental Engineering at MIT His research interests include materials science, computational mechanics, biomaterials, deformation and failure
Laurent Demanet
Ford Professor of Engineering, Department of Aeronautics and Astronautics, MIT
Professor of Applied Mathematics and Director of MIT’s Earth Resources Laboratory at MIT His research fields include scientific computing and applied analysis, with particular interest in analysis and algorithms for wave propagation, sparse and separated expansions, and inverse problems
Testimonial
"The course allowed me to put new knowledge into practice immediately through assignments, which deepened my understanding. The professors offered valuable insights and broadened my perspective, making the learning journey truly enriching."
.avif)
FAQs
Still have questions?
Will I receive any instructions after booking my interview?
Yes. Once your interview time is confirmed, you’ll receive detailed preparation guidance from the admissions committee to help you get ready.
What can a program advisor help with? Who are they?
Our program advisors are full-time team members with at least a master’s degree from top universities like Harvard University and Stanford University. They’ve helped thousands of students plan their paths—and they’re here to help you, too.
By understanding your background, goals, and questions, they can:
- Suggest the best-fit PBL and SPOC projects
- Help you build a strong application strategy
- Create a learning plan that matches your goals
Not sure if you're a fit yet? They’ll be honest with you. No pressure, no wasted time—just clear, helpful advice to move forward with confidence.
What should I include in my self-introduction?
You are encouraged to share your story, including but not limited to:
- Basic Information
- Educational History
- Relevant Project Experience
- Future Goals and Areas of Interest
- Top 3 PBL Courses of Interest
- Soft Skills
What questions should I expect during the interview?
Expect questions about your learning goals, learning strategy, interest areas, teamwork experiences, and motivation to join the program. When it comes to discussing specific SPOCs or PBLs, questions may also touch on your existing skills or relevant knowledge.
When and where do I submit my materials?
- Live Video Interview: Email materials to application@blendedlearn.org within 24 hours of your interview with the email subject: [Your Full Name] — AI+X Research Plan Admission Application
- Self-Paced Video Interview: Submit materials through the guided interview form.
Can I submit an unofficial transcript?
Yes, unofficial transcripts are accepted.
Do I need coding experience to apply?
No. There are no coding prerequisites. We welcome students from all academic backgrounds. Our projects have varying levels of difficulty, but our academic staff works with beginners to place them on teams with more skilled learners and prepare project leads to teach to their level. If you have any questions or concerns, please contact your Program Advisor.
Do I need an English test score (like GRE, TOEFL, IELTS)?
No. We believe language is a vital tool for learning and connection—but it shouldn’t be a barrier to accessing opportunities in AI+X. That’s why we do not require any English test scores. As long as you’re able to learn and communicate in English—whether naturally or with the help of AI tools—you’re welcome to apply.
Is there an age requirement for the program?
Yes. You must be at least 18 years old to join the on-campus experience. Exceptions apply for learners who are only participating in online learning.
I’m a freshman—how can I stand out when competing with more senior applicants?
You’re not at a disadvantage. Many of our participants are first- or second-year students who join to explore new fields, gain hands-on experience, and collaborate with peers from diverse backgrounds. In fact, starting early can be a unique advantage—it gives you more time to build skills, clarify direction, and benefit from the experience.
Our admissions team focuses on fit, not seniority. We look at how well the program aligns with your current goals and stage of growth. We assess each applicant within the context of their background, academic year, and potential, not by comparing freshmen to seniors or professionals. Show your initiative and curiosity—we’re looking for students ready to grow, wherever they are in their journey.
Who will review my application?
Your application will be reviewed by our admissions committee, which includes faculty, program alumni, industry partners, PBL academic coordinators, program advisors, and mentors.
Are seats limited every year?
Yes. To ensure a high-quality, collaborative learning experience, each PBL cohort is limited to 30 students and runs 3–5 times per year. Seats are offered on a first-come, first-served basis within the community. Once enrolled, you’ll gain access to your learner dashboard, where you can register for SPOCs and PBLs and manage your learning journey.
What if there’s no exact start date for the PBL projects I’m interested in?
At BlendED, we do our best to accommodate each learner and the academic team's preferred schedule. By using the "REQUEST" function in your dashboard, you can indicate your preferred start date for the next round of PBLs. So if your desired project isn't currently open, no worries—we'll help you join the waitlist and prepare for the next opportunity.
If I’m accepted, when will my learning plan begin?
If admitted, your learning plan officially begins with the start date of your first selected SPOC or PBL, NOT at the time of enrollment confirmation.
Why don’t you require English test scores (GRE, GMAT, IELTS, TOEFL)?
According to UNESCO and OECD, over 70% of college students worldwide are non-native English speakers. As AI advances, we believe language should no longer be a barrier to learning AI+X together on a global scale.
At BlendED, we embrace technology. As long as you’re adaptive and able to communicate effectively—with or without the help of AI tools—you’re welcome here. What matters most is your ability to learn, contribute, and grow in a collaborative environment.
Explore SPOCs
View All SPOCs
Transform Your Future with AI+X
Take control of your learning and start building your AI+X expertise.
