Dr. Mehdi Bayati

* Developing end-to-end digitalisation and process optimisation projects and scaling them to run in production environments using python ecosystem. * Responsible for collecting and refining data from different sources for developing new data driven products. * Automating and scheduling workflows using Apache Airflow.

Data science and computer vision in automotive sector Selected projects: • Vehicle color recognition: Fine-tuning pre-trained convolutional neural networks to learn classification based on color distribution, using object detection and segmentation models,i.e., Mask R-CNN. • Automating vehicle’s costs estimate: Applying machine learning methods to classify costs estimate of total loss vehicles into OK/not-OK cases using a small set of imbalanced training samples.

Computational modelling of biologically inspired neural networks; supervision of bachelor and master thesis; attending courses in machine learning and professional communication; Teaching assistant

Project: Study the role of learning rules and high-frequency pacemaker in formation of feed-forward structure in neural networks

Throughout this course, I have done few projects related to Data Engineering including Data Modeling With PostgreSQL and Apache Cassandra, Infrastructure setup on AWS cloud, Data Warehousing and Data Lake development With Spark, and Data Pipelines With Apache Airflow.

Project: Investigating the cognitive and neural mechanisms underlying learning and memory using computational methods

During my PhD program, I focused on understanding the cognitive and neural mechanisms underlying learning and memory in hippocampus, i.e., a brain region that involved in storing and retrieving episodic memories and in generating representations of space.

Thesis: Study the effect of synaptic plasticity on the structure and dynamics of networks of coupled neurons GPA: 1.7