Pouria Bahmanyar

Professional researcher with strong analytical and statistical skills, adept at designing and conducting experiments. Proven ability to collaborate effectively within team environments and adapt to changing project needs. Skilled in data analysis, literature review, and report writing. Known for reliability and results-driven approach.

• Autonomous Driving, Scene semantic segmentation using several Networks including DeepLab, DeepLabV3, U-NET and SegNet on CityScapes dataset with PyTorch
• Detecting Unexpected Obstacles On the Road Using Scene Segmentation For Self-Driving Cars with PyTorch
• Improvement of the results of the article Traffic Control Gesture Recognition for Autonomous Vehicles using CNN-LSTM model [Article], Using ResNet-18 to improve results of the article end to end for car steering wheel angle estimation
• Speech Recognition model using Lj speech dataset and Transformers with PyTorch
• Hands-on experience regarding training Recurrent Model using LSTM Network for language modeling with PyTorch
• Audio and Signal Processing, Training Recurrent Neural Network and one Dimensional CNN using PyTorch to recognize human activity using HAR dataset (Human Activity Recognition).
• Machine Vision, YOLO-v5 Model for face Detection using Wider-Face Dataset, Machine Vision model for car plate detection using YOLO-V7 with PyTorch, Car Plate Detection using YoLo v8 (using YoLo for detecting bounding box of plate and CNN for OCR using PyTorch

Digital System Design, 20/20, 

Micro-controllers and Micro-controllers Lab, 19.5/20, 

Communication Systems, 18.2/20, 

Signals and Systems, 20/20, 

Machine Vision, 17/20, 

Introduction to electronic 

Electrical and Electronic Components 

Machine Learning for All 

Neural Networks and Deep Learning 

Programming for Everybody 

Python Zero to Hero 

Machine Learning  

Deep Learning Zero to Hero 

• Autonomous Vehicles Driving
• Machine Vision
• Scene Semantic Segmentation
• Signal and Audio Processing
• Machine Learning
• Video & Image Processing

• Ranked 2nd among 120 undergraduate students in the Department of Electrical Engineering with a 1.9 (on German Grading System) GPA.
• Top 0.2% in the national university entrance exam among nearly 200,000 participants.
• Member of National Organization for Development of Exceptional Talents since 2010 (acceptance rate < 0.3%).
• Achieving 4th Rank among 400 teams at the FaceCup competition