DeepEigen

03/04/2024

Mr. Anand Mahindra, Chairman of Mahindra Group, praised our cutting-edge research at Swaayatt Robots, towards enabling Level-5 autonomous driving! :)

Jai Sri Ram 🙏 Jai Ma Kali 🙏

01/12/2021

We have launched a comprehensive Computer Vision course, covering its fundamentals and applications.

The theoretical depth of this course is higher than typical graduate courses (MS / M. Eng) in North American and European universities. Every topic covers the fundamental theory of the algorithms discussed under that topic, covering the theory almost from scratch.

After taking this course one would be able to acquire the knowledge required in the industry, and also be able to pursue an R&D career in perception, perception, or computer vision at large.

The assignments require coding almost all the algorithms (23 assignments) from scratch, without using any higher-level library. This ensures the ability to develop solutions in an industrial setting after taking the course.

The course, CV-1.0X Introduction to Computer Vision can be accessed at: http://www.deepeigen.com/courses

06/08/2020

Sanjeev Sharma, founder and CEO of Swaayatt Robots, having been researching automatic data-labelling at Swaayatt Robots (स्वायत्त रोबोट्स), where morphological operations are used before / after conditional random fields for accurate automatic data-labelling, shared his experience from multiple projects he's working on to present motivation behind the morphological operations.

This is video #59 of RO-1.0X: Introduction to and Visual Navigation course DeepEigen.

Course Webpage: https://lnkd.in/eC8uEbp

31/07/2020

Sample lecture covering the theoretical motivation behind using the Cumulative Distribution Function as a transformation function for an image histogram equalization (and also in adaptive methods).

This lecture ( # 36) is part our RO-1.0X and RO-2.0X Introduction to & Visual Navigation courses.

The datasets/images that were used for motivation and results of algorithms in Module-0, 1 and 2 were captured using our at Swaayatt Robots (स्वायत्त रोबोट्स).



Link to DeepEigen courses: https://lnkd.in/gMMhrcw

This lectures theoretically presenting the motivation behind the Cumulative Distribution Function as a transformation function used in the histogram equaliza...

28/07/2020

Sample video lecture ( #18) of the course RO-1.0X: Introduction to Robotics and Visual Navigation, on the topic of Uniform Noise Model.

This video also highlights the format of covering the mathematical parts of the lectures.

Furthermore, we have launched course RO-2.0X, which is RO-1.0X course without the planning module, and is interesting for those specializing in robotic perception and localization, as planning is usually an orthogonal topic.

All courses can be accessed here: http://www.deepeigen.swaayatt-robots.com/courses

14/07/2020

Introduction to Planning for Autonomous Vehicles and Robots.

In this lecture Sanjeev has mixed his experience in solving the in highly stochastic traffic dynamics of (at Swaayatt Robots (स्वायत्त रोबोट्स)) -- world's most difficult environment for autonomous driving to give an idea of what planning looks like for autonomous vehicles and in general.

This video is an introductory video of the course RO-1.0X: Introduction to Robotics and Visual Navigation.

Course web-page: https://lnkd.in/gHWnC8k

This video introduces planning and decision making under uncertainty for autonomous driving and robots in general. This is an introductory video for the cour...

07/07/2020

Introduction to Robotic Perception.

This is an introductory lecture video, by Sanjeev Sharma, of the course RO-1.0X: Introduction to Robotics and Visual Navigation.

Course web-page: http://www.deepeigen.swaayatt-robots.com/introductiontorobotics_coursedetails

This is an introductory lecture, of Module-0, of RO-1.0X Introduction to Robotics and Visual Navigation course.

16/06/2020

We have launched another course, RO-2.0X: Computer Vision for Robotics.

This is a very comprehensive course on (including covering ) for mobile robot applications. This course also discusses 4 research papers as case-studies.

This is a Category-II, self-paced course, with a 6 months access from the date of registration or start of the course (whichever is later).

The course is tentatively expected to start on August 20th 2020, and for early registrations we are offering a 30% Early Bird Discount. Financially weaker undergrad in can request additional discount by emailing us.

Register early to get the benefit of Early Bird Discount as it gradually reduces with time.

The instructor for this course is Sanjeev Sharma, Founder and CEO of Swaayatt Robots.



Course Page Link: http://www.deepeigen.swaayatt-robots.com/computervisionforrobotics_coursedetails

03/06/2020

Full outline of our AI-1.0X 2020: Machine Learning course in Category-IA.

Short, but theoretically very deep course. It will help registrants form deep mathematical foundation for many of our Category-II courses.

In 2019, it was supposed to be Category-I course, expanding to 30 weeks. Due to in-feasibility from business point of view, we have made only 7 weeks content available.

We have bifurcated Category-I into:
A- Category-IA: Full length Cat-IA courses exceed top graduate schools' courses on same topic, both in breadth and in depth of theory.

B- Category-IB: Cat-IB courses are similar in depth and breadth to one semester top graduate programs' course on same topic.

We will not be launching another Cat-IA course in 2020. We have plans though for full length Cat-IB courses in , machine learning, literature review, and mathematical optimization.

This AI-1.0X 2020 course also serves as a theoretical prior to our Category-II robotics course's deep learning module.

After taking this short course, registrants will have enough mathematical maturity to further study any ML / topic on their own.

Course Link: http://www.deepeigen.swaayatt-robots.com/machinelearning_coursedetails

28/05/2020

Full outline of our course RO-1.0X: Introduction to Robotics and Visual Navigation.

It is our Category-II course (description of Category-II is provided on DeepEigen websige), meaning it is theoretically deep enough from practical applications standpoint and doesn't go very deep in theory like Category-I courses (where Cat-I courses are comparable to graduate level theory (Cat-IB) and can even exceed their depth and breadth (Cat-1A)). Focus is more on practical applications.

Regarding Prerequisites:

For Module-II we expect familiarity with basic machine learning concepts, and knowledge of linear regression, logistic regression, gradient descent and sub-gradient descent. These can be learned via online tutorials or via first two weeks content of our AI-1.0X: Machine Learning course.

RO-1.0X course website: http://www.deepeigen.swaayatt-robots.com/introductiontorobotics_coursedetails