About Me
I just graduated from the University of Tehran with a degree in artificial intelligence and robotics. I’m an aspiring neuroscience enthusiast with an insatiable curiosity for understanding the intricacies of the human mind. I received my B.Sc. in Computer engineering from Babol Noshirvani University of Technology, Mazandaran. For my undergraduate project I worked with EEG signals to recognize emotions using Deep Reinforcement Learning.
I’ve always been curious about how our minds work. Why are we good at some things but struggle with others? Can we get better at what we’re good at and improve what we’re not so good at? I’m strongly confident that neuroscience has the capability to offer insights into these questions over time. By studying how the brain supports specific cognitive functions, researchers are beginning to identify patterns of neural activity associated with different mental tasks. Over time, this knowledge may enable us to refine brain function through targeted interventions—ranging from cognitive training programs to techniques like non-invasive brain stimulation and neurofeedback—grounded in empirical evidence and neurobiological mechanisms.
I hope to learn more about the brain and also help people in some way along the way. I recently defended my master’s thesis under the supervision of Dr. Mohammadreza Abolghasemi Dehaqani. In my thesis, we attempted to investigate the brain’s automatic change detection ability using a well-known neural signature called Visual Mismatch Negativity (vMMN).
Specifically, we investigated this Event-Related Potential (ERP) component based on the predictive coding hypothesis. We aimed to dissociate the repetition-related and expectation-related effects contributing to vMMN by designing a Rapid Serial Visual Presentation (RSVP) task paradigm and recording EEG signals from subjects. Our task was based on the study by Summerfield et al. (2008), with minor differences. The most significant modification was the use of complex visual stimuli. By adopting this approach, we were able to address a gap in previous work by separately investigating repetition and expectation, and also gain new insights about the brain’s processing of complex visual stimuli, rather than simple ones.
Most recently, I’ve been gravitating toward neuro-inspired computational models, particularly frameworks that draw from biological principles such as predictive coding, attractor dynamics, and neuromodulation. I’m interested in how these ideas can contribute not only to more interpretable and adaptable AI architectures but also to addressing some of the pressing challenges in current AI systems—such as robustness, continual learning, and generalization. By grounding machine learning models in the computational principles of the brain, I hope to contribute to the development of next-generation AI systems that are both cognitively informed and practically impactful.
Research Interests
Computational Neuroscience
NeuroAI
Vision Science
Decision Making
Interpretable AI
Education
MSc in Artificial Intelligence Engineering at University of Tehran, Tehran, GPA 19.12/20, 2021-2024
BSc in Computer Engineering at Babol Noshirvani University of Technology, Mazandaran, GPA 17.38/20, 2016-2021
Languages
Persian, English
Hobbies and Interests
Reading, Movies, Cooking, Gymnastics, Ballet, Painting