Neha Das

AI Researcher

India11 yrs 7 mos experience
Most Likely To SwitchAI Enabled

Key Highlights

  • Expert in data-driven models for human motion analysis.
  • Experience in reinforcement learning and human-robot interaction.
  • Proven track record in developing explainable AI solutions.
Stackforce AI infers this person is a Healthcare-focused AI researcher with expertise in reinforcement learning and human motion analysis.

Contact

LinkedIn

Skills

Core Skills

Artificial Intelligence (ai)Deep LearningMachine LearningSoftware DevelopmentData ScienceReinforcement Learning

Other Skills

Computer SciencePython (Programming Language)PyTorchMatlabOpenSimStatistical ModelingPythonWeb DevelopmentComputer VisionHealth InformaticsExplainable AIGenerative AIC++TensorFlowCreative Writing

About

I am currently a doctoral student at Technical University of Munich. My research focuses on creating data-driven models of human motion, especially for diagnosis and analysis of mobility disorders. Prior to this, I worked at Meta for year as an Artificial Intelligence (AI) Resident on Reinforcement Learning subproblems, specifically meta-reinforcement learning and learning from demonstrations. I am also interested in human-robot interaction and collaboration in the context of diagnosing and alleviating mobility issues, especially regarding learning robot policies for assisting humans for task completion. My other interests include reinforcement learning from human feedback, and its integration with sensor observations, generative modeling architectures such as VAEs, GANs, and diffusion models, and explainable models for classification and decision making.

Experience

11 yrs 7 mos
Total Experience
2 yrs 6 mos
Average Tenure
5 yrs 7 mos
Current Experience

Technical university of munich

Doctoral Student

Oct 2020 – Present · 5 yrs 7 mos

  • Developed explainable, data-driven algorithms for detecting anomalous motion in stroke patients using unsupervised anomaly detection techniques and generative modeling.
  • Designed inverse optimal control methods to mitigate compensatory (abnormal motion by stroke patients) movements via robotic feedback.
  • Implemented a data-driven framework for enabling FES-assisted motion through automatic detection of intended movements from muscular activity.
  • Led experimental studies - protocol design, participant recruitment, and creation of web-based tools
  • for motion data collection and labeling. Acquisition and processing of EMG-based, optical-marker, and
  • video-based datasets from healthy and post-stroke participants for model training and validation.
  • Proposed a novel uncertainty quantification approach for deep learning to detect data gaps via epistemic uncertainty estimation.
  • Designed methods to address dataset imbalance in PD symptom classification.
  • Designed the prototype for a web and mobile application for motion data visualization and PD symptom severity classification with interfaces for physicians and patients.
  • Developed a safe, user-preference–driven navigation framework using Preferential Bayesian Optimization.
  • Mentorship and teaching experience: Supervised over 15 undergraduate and graduate student thesis, as well as additional research and engineering practice projects; assisted with course organization, teaching, exam design and evaluation for several courses including Control Theory I and Student Seminar.
Computer ScienceArtificial Intelligence (AI)Deep LearningPython (Programming Language)PyTorchMatlab+4

Meta

AI Resident

Sep 2019 – Sep 2020 · 1 yr · Menlo Park, California, United States · On-site

  • Representation learning for robot manipulation: Contributed to the design of an extended body schema
  • of a robotic arm to enable manipulation of held tools from visual and proprioceptive inputs.
  • Model-Based Inverse Reinforcement Learning: Developed an inverse reinforcement learning approach
  • inspired by meta-learning, using gradient updates to efficiently robot behaviors from visual demos by humans.
  • Learning state-dependent losses for inverse-dynamics learning: Demonstrated that meta-learning
  • adaptive loss functions improves inverse-dynamics model learning for a robotic arm compared to conventional
  • fixed-loss approaches.
Computer ScienceComputer VisionArtificial Intelligence (AI)Deep LearningReinforcement Learning

Data​:lab munich

2 roles

Master Thesis Student

Sep 2018 – Sep 2019 · 1 yr

Computer ScienceComputer VisionDeep Learning

Intern

Jun 2018 – Sep 2019 · 1 yr 3 mos

Computer Science

Technical university munich

2 roles

Working Student

Jun 2017 – Mar 2018 · 9 mos · Greater Munich Metropolitan Area

  • Under the Chair of Robotics, Artificial Intelligence and Real-time Systems, TUM, I worked on two projects:
  • 1. Matlab and Simulink implementation of the tutorials for the course Cyber-Physical Systems.
  • 2. Design and Development of the CommonRoad Website - https://commonroad.in.tum.de/
Computer ScienceDeep Learning

Master Student

Oct 2016 – Sep 2019 · 2 yrs 11 mos · Greater Munich Metropolitan Area

  • My projects during the masters course include :
  • 1. Fast Semantic Segmentation of Human Body from Depth images - using depth-separable convolutions and other optimizations with U-Nets
  • 2. Deriving Depth Images from RGB data.
  • 3. Modelling Latent Dynamic Systems with Inverse Autoregressive Flow
  • 4. Implementation of Importance Weighted Autoencoder and evaluation on MNIST data.
  • 5. Analysis and comparison of several Iterative Closest Point algorithms used in 3D reconstruction techniques.
  • You can find the code repositories for all these projects on my github page: https://github.com/neha191091
Computer ScienceComputer VisionArtificial Intelligence (AI)Deep Learning

Epic

Software Developer

Oct 2014 – Oct 2016 · 2 yrs · Greater Madison Area

  • Primary Responsibilities included front-end and back-end development of Web-based applications
  • Worked on the design and development of a new web-based module tailored to the needs of a Gastroenterology Department in hospitals
  • Worked on an existing module for the Bed Management of the Hospital.
  • Worked on a subproject for the development of linter that statically analyses the server side code and prints out documentation errors
Computer Science

Mcafee

Software Developer in Test

Jul 2013 – Aug 2014 · 1 yr 1 mo

  • As a SDET at McAfee I was responsible for:
  • 1. Debugging issues in the software and fixing errors
  • 2. Validating and optimizing any new or corrected code
  • 3. Adding to test automation framework.
  • I also worked on project for creation of an indigenous Stress Framework which can simulate real world I/O operations in for performance testing of our software as well as for validation of its operations.
Computer Science

Tata consultancy services

Intern

Jun 2012 – Jul 2012 · 1 mo · Gurugram, Haryana, India

  • worked in along with the testing team for a project
Computer Science

Bharat heavy electricals limited

intern

Dec 2011 – Dec 2011 · 0 mo

  • worked on the development of a sub contracting system software
Computer Science

Wipro technologies

intern

Jun 2011 – Jul 2011 · 1 mo

  • worked on computer networking
Computer Science

Education

Technical University of Munich

Master's degree — Computer Science

Jan 2016 – Jan 2019

Delhi College of Engineering

Bachelor of Technology (BTech) — Computer Science

Jan 2009 – Jan 2013

Stackforce found 100+ more professionals with Artificial Intelligence (ai) & Deep Learning

Explore similar profiles based on matching skills and experience

Arush Pettem

Arush Pettem

Marketing Team Lead

at Incident NITK

India0 mo exp
VS

Vyshnavi Sharma

Accumulated Expertise

at Career-Wide Experience

Hyderabad, India0 mo exp
PS

Prachi Singhal

Software Engineer

at Microsoft

Bengaluru, India7 yrs 8 mos exp
Rohan Dixit

Rohan Dixit

Chief Data Scientist

at Blackstone

Delhi, India0 mo exp
Data ScienceAI
Muskan Dosi

Muskan Dosi

Accumulated Expertise

at Career-Wide Experience

Jaipur, India0 mo exp
Ishan Gupta

Ishan Gupta

Software Engineer 2

at Uber

Bengaluru, India4 yrs 6 mos exp
Manas Mehta

Manas Mehta

Accumulated Expertise

at Career-Wide Experience

Ahmedabad, India0 mo exp
Raghul Rajasekar

Raghul Rajasekar

Senior Software Engineer

at Google

Mountain View, United States5 yrs 9 mos exp