0% found this document useful (0 votes)
382 views7 pages

Vizuara SciML Bootcamp Details

Uploaded by

Nagaraja E
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
382 views7 pages

Vizuara SciML Bootcamp Details

Uploaded by

Nagaraja E
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Vizuara Scientific Machine Learning Bootcamp

Transition to ML | Hands on industrial projects | Path to ML research

We, Dr. Raj Dandekar, Dr. Rajat Dandekar and Dr. Sreedath Panat, are team Vizuara. After
graduating as toppers from our respective departments at IIT Madras, we finished our PhDs at MIT
and Purdue in 2022.

In less than 3 years, Dr. Raj Dandekar went from a complete beginner to finishing a PhD, having
400+ citations and getting multiple job offers in machine learning (ML). We have created this
bootcamp to help you make the transition to ML and publish research.

At the heart of this course is a new and emerging field of Scientific Machine Learning (SciML). This
field combines the knowledge of scientific disciplines with ML. You will master SciML after
completing this course.

This is not a traditional ML course. In this course, you will not be doing toy Kaggle projects. We will be
working with real life data and projects such as Covid-19 pandemic modeling using ML, Black hole
modeling using ML, biological and environmental modeling using ML.

Bootcamp objectives
1. You will confidently transition to ML
2. You will have done impactful, hands on ML projects which you can add to you CV.
3. You will learn to identify ML problems in your field of study and independently start projects.
4. You will learn how to convert your results into a research paper.
5. You will learn and master the field of Scientific Machine Learning.
6. You can email professors and start ML projects with them. This will boost your profile and help
you in placements, grad school applications!
Bootcamp Content
Lecture No. Lectures Module What you will learn

1 Introduction: Transitioning to ML Introduction to the course


How traditional ML is taught
Introduction to SciML
Introduction Basics of SciML
Scientific Machine Learning (SciML)
2 Problems which can be solved using SciML
technical overview
Learnings from this course
How can you transition to ML?

Installing and understanding the Julia Introduction to Julia


3 What is Julia?
programming language Why Julia is the coolest new language?

4 Running ODEs in Julia What are ODEs and PDEs?


Building your first ODE in Julia using hands on
Differential Equations
examples
in Julia
5 Running PDEs in Julia Building your first PDE in Julia using hands on
examples

Neural Networks introduction What are weights, biases, activation functions?


6 Gradient Descent introduction ML Basics What is gradient descent optimization?
Backpropagation introduction How are weights of neural networks optimized?

Physics Informed Neural Networks -


7 What are Physics Informed Neural Networks
Theory
(PINNs)?
Physical Informed Neural Network - Building your first PINN in Julia
8 Applications of PINNs
Practical

9 Neural ODE - Theory The 3 Pillars of What are Neural ODEs?


Scientific Machine Building your first Neural ODE in Julia
10 Neural ODE - Practical Learning Applications of Neural ODEs

Universal Differential Equation- What are Universal Differential Equations


11
Theory (UDEs)?
Building your first UDE in Julia
Universal Differential Equation -
12 Applications of UDEs
Practical

Research Project 1: Covid-19 infection Introduction to the problem


13
prediction using SciML Formulating a story
Hands on research Boiling down the problem to a SciML problem
projects Running the code in Julia
Research Project 2: Black hole
14 Plotting figures
dynamics using SciML
Add project to your CV

What is a research paper and how different is it


from a project?
How to write a research Paper title and abstract
15 Converting results to research
paper? Paper introduction
Paper figures
Paper conclusion

In each lecture, you will get:


1. Access to videos
2. Access to all code files used during the lectures
3. Lecture Notes
4. Homework assignments
4 ways you can access the bootcamp
Student Plan 20000 Rs

Lifetime access to all videos, codefiles, homework assignments

Community Plan 45000 Rs

Lifetime access to all videos, codefiles, homework assignments


Access to bootcamp community on Discord
Student collaborations on Discord --> potential publications.
Assignment checking, doubt clearance to lectures/assignments
Free access to all ML webinars conducted throughout the year

Researcher Plan 95000 Rs

Lifetime access to all videos, codefiles, homework assignments


Access to bootcamp community on Discord
Assignment checking, doubt clearance to lectures/assignments
Free access to all ML webinars conducted throughout the year
Access to open list of research problems in SciML
Selection of research topic
4 month personalized guidance in doing research on the topic
Publishing the research in conferences/journals

Industry Professional Plan 120000 Rs

Lifetime access to all videos, codefiles, homework assignments


Access to bootcamp community on Discord
Assignment checking, doubt clearance to lectures/assignments
Free access to all ML webinars conducted throughout the year
Access to open list of research problems in SciML
Selection of research topic
4 month personalized guidance in doing research on the topic
Publishing the research in conferences/journals
AI in industry: Lectures on Generative AI, LLMs
Industry AI doubt clearance forums
We will act as advisors for AI integration in your industry.
4 ways you can access the bootcamp
Student Community Researcher Industry
Features
Plan Plan Plan Plan

Access to all video lectures

Access to all code files used during


lectures

Homework assignments

Access to bootcamp community

Doubt clearance by founders

Assignment checking

Free access to SciML webinars


conducted throughout the year

Access to open list of research problem


in SciML

Selection of research topic

Guidance on doing research on chosen


topic:
Literature review
Paper writing
Submitting to conferences/journals

Path to ML publication in the selected


topic

AI in industry: speaker sessions from


top industry experts

Industry AI doubt clearance forums


List of research projects (Researcher, Industry Plan)

Epidemiology:

1. Application of QSIR model to Covid-19 infections in India 2022.


2. Comparison of Quarantine strength in India from 2020-2023.
3. Comparison of global quarantine strengths as the Covid-19
pandemic progressed.
4. A novel look at epidemiology compartment models using
Scientific Machine Learning.
5. Neural ODEs vs Universal Differential Equations capabilities in
forecasting.
6. Role of Neural Network architecture in SciML for epidemiology

Physics:
1. Symbolic recovery of Relativistic Corrections in Black Hole
dynamics
2. The predator-prey model: A SciML perspective (PINNs, Neural
ODEs, UDEs)
3. Bayesian Neural ODE for the predator prey model
4. Role of Neural Network architecture in training PINNs: wave
equation

Mechanical Engineering:

1. Recovery of autocatalytic reactions (Brusselator) in combustion


systems
2. Role of SciML in Hooke’s Law
3. Solving the Brusselator using Physics Informed NN
4. Missing term recovery in beam dynamics
List of research projects (Researcher, Industry Plan)

Chemistry-Biology:

1. Recovery of actual reaction in Michaelis-Menten kinetics


2. Recovery of actual reaction in Hodgkin-Huxley Model

Economics:

1. Symbolic recovery of Relativistic Corrections in Black Hole


dynamics
2. The predator-prey model: A SciML perspective (PINNs, Neural
ODEs, UDEs)
3. Bayesian Neural ODE for the predator prey model
4. Role of Neural Network architecture in training PINNs: wave
equation

Material Sciences:

1. SciML for battery degradation


2. SciML for sintering dynamics

Astronomy:

1. UDEs for two body problems


2. UDEs for N body problems
3. Missing term recovery in Stellar Structure Equations
4. Role of Neural ODEs in Astronomy problems
5. Role of Bayesian Neural ODEs in two body problems
6. Missing term recovery in Chandrasekhar's White Dwarf Equation.
FAQ
1) Who are the organizers of this bootcamp?
This bootcamp is organized by Dr. Raj Dandekar (MIT AI PhD, IIT Madras BTech), Dr.
Rajat Dandekar (Purdue PhD, IIT Madras MTech), Sreedath Panat (MIT PhD, IIT
Madras BTech). The creators of this Bootcamp are trained in the field of Scientific Machine
Learning, from the pioneers of this field at MIT.

2) Is my background suitable?
We have made different plans: Student, Community, Researcher and Industry Professional.
We have made these plans in such a way that whether you are a beginner or an intermediate
or someone looking for research exposure or someone in industry, this bootcamp is suitable
for all.

3) Are the fees non-refundable?


Yes, fees for this program are non-refundable. We are very confident in the material which
we have prepared, after hard work of multiple years.

4) Will the bootcamp be in person or online?


The bootcamp is entirely online.
Student plan: online content accessible to students.
Community plan: access to Discord community maintained by organizers of the bootcamp.
Researcher plan: access to Discord community + personal chat group with founders.
Industry Professional plan: access to Discord community + personal chat group with
founders.

5)I am in a different time zone. Can I still attend the bootcamp?


Yes, 100%. One reason why we don’t have live classes is that we want the bootcamp to be
accessible to students of multiple time zones.

6) How much time do I need to devote for this bootcamp?


There are ~15 lectures with coding and assignment. If you devote 3-4 days to understanding
one lecture and completing the assignments diligently, you should be able to complete the
bootcamp material in 2 months.

7) I am an industry professional/ doing a PhD. Can I manage this simultaneously?


Yes, 100%. You can watch the lectures at your own pace and get comfortable with the codes
and the assignments. You have lifetime access to all materials.

8) For the researcher plan, how much time of personalized assistance will I get for
publishing paper?
You will receive 4 months of personalized assistance. We will work on everything together:
right from topic selection, literature review, drafting the paper and the submission.

For more questions email to [email protected]

You might also like