Tina Falak Doust

From data to decision is a journey through a space where systems learn to think.
Here lies a record of building, investigating, and evolving that space through research and practical experimentation.

Portfolio

An overview of work defined by inquiry and hands-on exploration, covering research efforts, technical achievements, and key qualifications.

Education

2021 - 2025

Bachelor of Engineering - BE, Computer Engineering

University of Guilan

Sep 2018 - Jun 2021

High School Diploma

Yekan Highschool

Certificates

Machine Learning Specialization

Coursera - 2023

Network+

Arjang institute - 2024

Data Analytics Bootcamp

Tehran University - 2022

Projects

Here, concepts turn into reality through systems that learn, adapt, and act. Each project maps a process: from framing the problem to applying the right methods and completing the build. Technical details, code, and extra materials are shared where relevant.

Image Captioning

Automatically producing captions for images is a demanding task, vital to accessibility, search, and media applications. This project applies the Flickr8k dataset to train a hybrid model: CNNs capture visual details, while RNNs generate coherent textual descriptions.

PyTorch OpenCV

View on GitHub

Age Estimation with ResNet

This project aims to improve the accuracy and adaptability of age estimation models by leveraging the power of ResNet architectures. The current age estimation models, primarily based on PyTorch and convolutional layers, often face limitations in terms of accuracy and generalization across diverse datasets like UTKFace.

OpenCV PyTorch

View on GitHub

Language Modeling with LSTM and AWD-LSTM on WikiText-2

In NLP, language modeling focuses on predicting the next word based on prior context. This work implements and evaluates two models: Base Model: A conventional LSTM language model. Improved Model: An AWD-LSTM applying techniques such as weight dropping, variational dropout, and ASGD optimization to boost accuracy and robustness.

Pytorch

View on GitHub

Competitions & Achievements

Challenges tackled, skills demonstrated, and recognition earned through competitive programming and AI competitions.

Kaggle - CMI Detect Behavior with Sensor Data

🏆 Ongoing

2025 - Predicting Body Focused Repetitive Behaviors from a Wrist-Worn Device

Kaggle - MITSUI&CO. Commodity Prediction Challenge

🏆 Ongoing

2025 - Developing a robust model for accurate and stable prediction of commodity prices

Publications

Research bridging learning, language, and autonomy.
Showcased here are peer-reviewed studies, ongoing partnerships, and contributions to the AI field at large.

DreamerAgent: A Computational Model of the Lacanian Unconscious Using Memory-Driven Signifier Activation and Neurochemical Emotional Modeling

2025 Preprint avaiable on SSRN

AmirMahdi Aramideh, Tina Falak Doust Noshary, Ehsan Kozegar

This paper presents DreamerAgent, a novel AI framework that integrates Lacanian psychoanalytic theory with modern language and vision models to simulate a symbolic unconscious. Using dream narratives, emotional modeling, and memory-driven signifier activation, it enables AI agents to exhibit human-like symbolic complexity, contradiction, and emergent psychological behaviors.

Paper Code