Computational Neuroscience· Cognitive Psychology. AI

Shokoofeh
Hosseini

MSc Computational Neuroscience at BCCN Berlin. I bridge machine learning and brain science — explore the intersection of neuroscience, machine learning, and cognitive science. Building models that predict human perception and higher brain functions.

Background

I am a researcher at the intersection of computational neuroscience, computer vision, and cognitive science, currently completing my MSc at the Bernstein Center for Computational Neuroscience (BCCN), Berlin. My primary research interest concerns the computational principles underlying human visual attention — specifically, how structured semantic representations of dynamic environments relate to the goal-directed nature of gaze behaviour.

As a Student Assistant at the Science of Intelligence Excellence Cluster (SCIoI, TU Berlin), I develop end-to-end pipelines that link open-vocabulary scene graph representations with human gaze scanpaths. This work combines vision-language models for relational scene parsing, GloVe-based predicate embedding, and K-medoids clustering to investigate which semantic relation families in dynamic scenes are preferentially selected by human visual attention. During my lab rotation at the NeuroImaging Group (BCCN), I applied multivariate pattern analysis (MVPA) to real fMRI data, evaluating experimental design validity through the Same Analysis Approach (SAA) and The Decoding Toolbox (TDT) within the SPM framework.

Prior to my transition into neuroscience research, I accumulated over a decade of experience in software engineering and systems architecture, with a focus on large-scale SaaS development and enterprise-grade distributed systems. This background informs a rigorous, reproducibility-oriented approach to computational research.

My broader interests lie in the representational basis of perception and cognition — how symbolic, geometric, and neural representations can be integrated to model the selectivity and flexibility of biological intelligence.

Research Interests
Vision & Attention
Visual Attention Gaze Behaviour Modelling Scene Graph Generation Eye Tracking
Neuroimaging
fMRI Decoding MVPA Experimental Design Evaluation Brain Representations
ML & Representations
Vision-Language Models Semantic Embedding Representation Learning Clustering

Professional Journey

Student Assistant — Gaze Behavior Modeling Jul 2025 – Present
SCIoI (TU Berlin), Berlin

Building a pipeline that links open-vocabulary scene graphs from dynamic videos with human gaze scanpaths (Project 57). Constructs frame-wise scene graphs via VLM, extracts foveation-based temporal relations from eye-tracking data, embeds predicates using GloVe, clusters them with K-medoids, and identifies which semantic relation families are preferentially selected by human visual attention.

Verified · SCIoI Profile Page
Lab Rotation — NeuroImaging Group Sep 2025 – Nov 2025
NeuroImaging Group's Lab, BCCN, Berlin

Analyzed fMRI data using the Same Analysis Approach (SAA) and The Decoding Toolbox (TDT) within SPM. Created a tutorial demonstrating these tools for the lab.

Senior Scrum Master Jun 2020 – Sep 2024
Dotin — ESB Project, Tehran

Led agile delivery across 4+ teams (~30 people) in an Enterprise Service Bus project, collaborating with Product Owners to align technical delivery with customer needs.

Senior Java Developer Dec 2014 – Jun 2020
Dotin — CMS Project, Tehran

Developed SaaS banking solutions (Card Management System). Specialized in synchronized programming, data access control, and open banking APIs.

Java Developer Jan 2012 – Dec 2014
PooyaCo — MCDS Project, Tehran

Contributed to the Central Deposit System using REST/SOAP architecture in a cross-functional team.

Technical Stack

Languages
Python Java 8+ R MATLAB HTML CSS JavaScript
ML / AI Libraries
PyTorch Scikit-Learn Transformers OpenCV Pandas NumPy
Neuro & Imaging
SPM TDT SAA MVPA fMRI Analysis
AI / Research Methods
LMM ViT Deep Learning Dimensionality Reduction Clustering Pattern Recognition
Visualization
Matplotlib Seaborn
Engineering & Agile
Scrum REST / SOAP SaaS Open Banking Git

Selected Work

ConceptGraph
↗ GitHub

Exploration of graph-based conceptual representations — building structured semantic graphs connecting concepts and their relationships. Part of ongoing interest in combining symbolic and neural approaches to knowledge representation.

Python Graph Theory Knowledge Representation
Scene Graph Generation & Human Visual Attention
↗ SCIoI Project 57

Research question: Which semantic relation clusters in an open-vocabulary scene graph are preferentially selected by human gaze in dynamic environments?

This project investigates the link between structured scene representations and human visual attention. The full pipeline constructs open-vocabulary scene graphs from dynamic videos, extracts gaze-based temporal relations from eye-tracking scanpaths, and compares which semantic relation types humans preferentially attend to — distinguishing between relations that are merely frequent in the environment versus those actively selected by attention.

STEP 01
Scene Graph Construction
Per-frame object detection, bounding boxes & pairwise relation inference via VLM → JSON scene graphs
STEP 02
Temporal Relation Extraction
Foveation events from eye-tracking data → attended objects → scanpath-based relation sequences
STEP 03
Embedding & Clustering
GloVe predicate embeddings (300-dim) → cosine similarity → K-medoids semantic families
STEP 04
Attention Analysis
Compare scene-wide relation distribution vs. gaze-selected relations to identify attentional preference
Python 3.13 VLM GloVe Embeddings K-medoids Eye Tracking Scene Graphs UVO Annotations SCIoI / TU Berlin
fMRI Experimental Design Evaluation — NeuroImaging Rotation
BCCN Berlin

Goal: Evaluate the validity and decoding reliability of an ongoing lab experiment using real fMRI data.

As part of my lab rotation at the NeuroImaging Group (BCCN Berlin), I worked with real fMRI data from an active research project. I applied the Same Analysis Approach (SAA) to assess whether the experimental design could support robust, reproducible decoding — a principled method that tests whether the same analytical pipeline succeeds on real data but not on permuted controls, directly probing design validity before drawing scientific conclusions.

Decoding was carried out using The Decoding Toolbox (TDT) within the SPM framework, applying multivariate pattern analysis (MVPA) to identify brain regions whose activation patterns reliably distinguish experimental conditions. As a final deliverable, I produced a step-by-step tutorial covering the full SAA–TDT workflow to help the lab run reproducible analyses in future projects.

MATLAB SPM TDT SAA MVPA fMRI Experimental Design
Customer Satisfaction Prediction with Michigan-Style LCS
↗ Published Paper

Problem: Predicting bank customer satisfaction from a high-dimensional, severely class-imbalanced dataset (96% satisfied vs. 4% unsatisfied) using an interpretable rule-based learning system.

Applied a Michigan-style Learning Classifier System (LCS) — a genetic-based machine learning approach that evolves a population of IF:THEN rules — to classify Santander Bank customers. The raw dataset contained 369 anonymized features across 147,392 records. A rigorous preprocessing pipeline handled class imbalance via SMOTE, removed constant and highly-correlated features (threshold: 0.85), and converted all attributes to binary format for rule-based processing.

Three rule compaction strategies were benchmarked — QRC, QRF, and PDRC — using 5-fold cross-validation. QRC achieved the highest accuracy (88.4%), while QRF was the fastest. Attribute Tracking and Feedback mechanisms further identified the four most predictive features driving customer dissatisfaction.

88.4%
Best test accuracy (QRC)
147K
Records after SMOTE balancing
3
Rule compaction strategies compared
R Michigan-Style LCS ExSTraCS SMOTE Rule Compaction GBML 5-Fold CV CiDaS 2019

Research ↗ Google Scholar

Human Resource Allocation to the Credit Requirement Process: A Process Mining Approach
IEEE — 13th International Conference on Information & Knowledge Technology (IKT), Dec 2022
Hosseini, S., Ebadati, O.M., Mehrabioun, M.
doi:10.1109/IKT57960.2022.10039030 ↗
Customer Satisfaction Prediction with Michigan-style Learning Classifier System
International Conference on Contemporary Issues in Data Science (CiDaS), March 2019 — SN Applied Science
Borna, K., Hosseini, S. & Aghaei, M.A.M.
doi:10.1007/s42452-019-1493-1 ↗

Academic Background

MSc Computational Neuroscience
Bernstein Center for Computational Neuroscience (BCCN), Berlin
2024 – Present
Data Science Certificate
Khatam University, Tehran — Statistics · Python · Deep Learning · Big Data
Nov 2022 – May 2023
MSc Information Technology Management
Kharazmi University, Tehran
Feb 2019 – Nov 2022
BSc Computer Science
Kharazmi University, Tehran
Sep 2007 – Sep 2011

Get In Touch