CV
You can downlaod a pdf of my CV above.
Basics
Name | Ram Eshwar Kaundinya |
Role | Neuromoprhic AI Researcher and AI Engineer |
r.e.kaundinya@rug.nl | |
Url | https://rkaundinya.github.io |
Summary | PhD Candidate at the University of Groningen researching neuromorphic computing for tactile and sensorimotor applications. Strong interest in cognitive architectures, dynamical systems theory, control theory, cognitive science, and philosophy. A veteran video game engineer working alongside renowned developers from Call of Duty, World of Warcraft, LEGO, Civilization, XCom, Skyrim, the Sims, and more. |
Work
-
2024.09 - 2029.03 PhD Candidate at Cognigron
University of Groningen
I work at the intersection of neuromorphic computing, artificial intelligence, cognitive science, dynamical systems, and control theory. I am a part of the Cognigron center and the NWO funded NL-ECO project. I have a particular interest in the application of dynamic reconstructive memory architectures for real-time sensorimotor control tasks. I am also interested in embodied AI and the applications of self-organizing systems to building intelligence from the ground up. I am interested in the intersection of relevance realization and dynamical systems theory.
-
2024.03 - 2025.07 Gameplay Engineer
Midsummer Studios
I worked as an engineer at Midsummer Studios founded by Jake Solomon, Will Miller, and Nelsie Birch on a life simulation game. My work remains confidential, but involved elements of implementing novel artificial intelligence pipelines, cloud engineering, telemetry, and edge compute optimizations.
Education
-
2024.09 - 2029.03 Groningen, Netherlands
-
2022.03 - 2024.03 Philadelphia, USA
-
2015.09 - 2019.06 Los Angeles, USA
Awards
- 2024.03
Honors Society
Upsilon Pi Epsilon
Honors Society award for excellence in the field of computer science awarded at Drexel University for my masters work.
Certificates
Nonlinear Dynamics - Mathematical and Computational Approaches | ||
Santa Fe Institute | 2025-07-18 |
Publications
-
2025.07.08 Biologically-Inspired Representations for Adpative Control with Spatial Semantic Pointers
IEEE
We explore and evaluate biologically-inspired representations for an adaptive controller using Spatial Semantic Pointers (SSPs). Specifically, we show our method for place-cell-like SSP representations outperforms past methods. Using this representation, we efficiently learn the dynamics of a given plant over its state space. We implement this adaptive controller in a spiking neural network along with a classical sliding mode controller and prove the stability of the overall system despite non-linear plant dynamics. We then simulate the controller on a 3-link arm and demonstrate that the proposed representational method gives a simpler and more systematic way of designing the neural representation of the state space. Compared to previous methods, we show an increase of 1.23-1.25x in tracking accuracy.
Skills
Languages and Frameworks | |
Python | |
C | |
C++ | |
C# | |
Java | |
Unreal Engine | |
Unity | |
Nengo | |
SNNTorch | |
PyTorch | |
ACT-R | |
Docker |
Topic Areas | |
Neural Networks | |
Reinforcement Learning | |
Neuromorphic Computing | |
Artificial Intelligence | |
Cognitive Science | |
Dynamical Systems | |
Control Theory | |
Game Development |
Languages
English | |
Native speaker |
Telugu | |
Conversational |
Spanish | |
Basic |
Interests
Philospohy | |
Neoplatonism | |
Vedanta | |
Mysticism | |
Alfred North Whitehead | |
Spinoza | |
Alan Watts | |
Jiddu Krishnamurti | |
Aristotle | |
Plato | |
Socrates | |
John Vervaeke |
Engineering | |
Thousand Brains Theory | |
Dynamical Systems | |
Control Theory | |
Reinforcement Learning | |
Neural Networks | |
Neuromorphic Computing | |
Robotics |