Pulin Agrawal

Researcher and Educator

On the stepping stones to build machines that can think like us.

I am on a journey to build human-like intelligence in machines or otherwise called Artificial General Intelligence (AGI). Once I am done and dusted, computers will be so smart that your wish will be your command, literally!

I helped build a computer vision based cognitive agent for nFlux Inc. to assist NASA astronauts during deep space exploration. I also designed an automated trading platform inspired by the predictive computations in brains, which is profitable and live, for Intelletic Inc. Embarking on a journey to create and disseminate knowledge about intelligence at Penn State.












I completed my doctorate in Computer Science from the University of Memphis, Memphis, TN. My dissertation aimed to present sparse representations as a robust representation tool for various applications in AI. I did my Bachelors in Technology in Computer Science from IP University, Delhi, India and Masters in Applied Computer Science and specialization in Cognitive Science also from the University of Memphis. I co-chaired the 12th Artificial General Intelligence conference in Shenzen, China and I have published work on computations in the neocortex, memory architecture and philosophy of self for cognitive agents.


I have worked as a research consultant for Intelletic Corporation LLC, Naperville, IL, USA. There I provided consulting on building predictive analytics model which led to a successful futures trading strategy. At nFlux, I am worked on and writing grants for NASA, USAF and NSF to bring cognitive agent and computer vision-based assistance to astronauts in space and operators on Earth.


I enjoy coding in and teaching Python. I am passionate about curiosity motivated active learning approach to teaching. When not involved with any of the above I love to think and talk about biology, astrophysics, design, technology, Hindi, Spanish and Japanese.

Lifeboat Foundation's take on my profile

Dr. Pulin Agrawal

Pulin Agrawal, Ph.D. is an Artificial General Intelligence and Cognitive Science Researcher, and Engineer at The University of Memphis, Tennessee.

Pulin is leading the development of more sophisticated artificial general intelligence based agents and helping in finding biological patterns amid the data points. He has been working as a Research Assistant since 2011, focusing on the LIDA cognitive architecture, including Sensory Memory, Self-Systems, and Sensory Motor Memory.

Between 2014 and 2016, Pulin was Teaching Assistant for subjects like Information Retrieval, Natural Language Processing, Web Services, and Cryptography.

The LIDA (Learning Intelligent Distribution Agent) cognitive architecture is an integrated artificial cognitive system that attempts to model a broad spectrum of cognition in biological systems, from low-level perception/action to high-level reasoning. Developed by Stan Franklin and colleagues at the University of Memphis, the LIDA architecture is empirically grounded in cognitive science and cognitive neuroscience. In addition to providing hypotheses to guide further research, this architecture can support control structures for software agents and robots.

Pulin, together with the creator of IDA and LIDA models, published A LIDA cognitive model tutorial in 2016. Providing plausible explanations for many cognitive processes, the LIDA conceptual model is also intended as a tool with which to think about how minds work.

With Stan Franklin, he also published research on Multi-layer Cortical Learning Algorithms (CLA). CLAs are an attempt by Numenta to create a computational model of perceptual analysis and learning inspired by the neocortex in the brain. In its current state only an implementation of one isolated region has been completed. The goal of the paper is to test if adding a second higher level region implementing CLAs to a system with just one region of CLAs, helps in improving the prediction accuracy of the system. The LIDA model can use such a hierarchical implementation of CLAs for its Perceptual Associative Memory.

In 2015 Pulin, together with Stan Franklin, coedited and published research about Estimating Human Movements Using Memory of Errors. This research was inspired by a study in neuroscience described in A Memory of Errors in Sensorimotor Learning.

Briefly, Pulin joined Intelletic Trading Systems in 2016 as a Research Consultant, providing consulting on the prediction algorithm of futures trading systems and utilized a model inspired from computations in the brain for predictions. This system is trading live.

He earned his Ph.D. in Computer Science in 2019 and his Master’s Degree in Applied Computer Science in 2013 from The University of Memphis. Before coming to Memphis, he graduated from Guru Gobind Singh Indraprastha University in India, where he earned his Bachelor’s Degree of Technology in Computer Science in 2011.

Pulin is also an attendee a co-Chair of the 12th International Conference AGI 2019 in Shenzhen, China, and coeditor of Artificial General Intelligence: 12th International Conference, AGI 2019, Shenzhen, China, August 6–9, 2019, Proceedings.

His latest work Sensory Memory For Grounded Representations in a Cognitive Architecture, was presented and published in 2018 at the Sixth Annual Conference on Advances in Cognitive Systems.

(click here for the original post)

Find out more at