Deep learning applied to neuroscience data

In this cutting-edge project, I developed an innovative approach to classify neuronal cell types using deep learning techniques. The goal was to automate and improve the accuracy of neuronal cell classification, a crucial task in neuroscience research.

Key features of the project:

Data Transformation: Converted complex electrophysiological spike waveforms into 2D images using Gramian Angular Fields (GAFs).

Deep Learning Model: Designed and implemented a Convolutional Neural Network (CNN) tailored for analyzing the GAF images.

High Performance: Achieved superior accuracy in classifying three neuronal cell types (Pyramidal cells, Interneurons, and unclassified cells) compared to traditional methods.

Scalability: The approach is efficient and can handle large datasets, making it suitable for extensive neuroscience studies.

Interdisciplinary Application: Successfully combined machine learning with neuroscience, demonstrating the power of AI in advancing scientific research.

This project showcases my expertise in deep learning, data preprocessing, and applying AI to complex scientific problems. It demonstrates my ability to innovate and deliver high-impact solutions that can significantly advance research in fields like neuroscience.