I am Alireza Mansouri, a passionate Machine Learning and Software Engineer with a focus on optimization techniques for machine learning and deep learning. My professional journey includes designing scalable software solutions, developing efficient machine learning models, and contributing to open-source projects. I thrive at the intersection of research and application, aiming to create impactful solutions in AI. My key interests include enhancing model performance through optimization and exploring hardware acceleration for neural networks.
Developed a hybrid optimization algorithm combining conjugate gradient methods with the Adam optimizer, achieving faster convergence on benchmark datasets. [GitHub]
Built a scalable machine learning pipeline using Docker and Kubernetes for efficient model training and deployment. [Live Demo]
Collaborated on an FPGA implementation to accelerate neural network inference, outperforming traditional CPU/GPU setups. [Report]