My Journey in Machine Learning and Object Detection The first time I watched a computer accurately identify objects in an image, I knew machine learning and object detection would define my career. That initial spark grew into a decade-long journey of learning and innovation, shaping how I solve problems. My exploration began during my computer science undergrad. An AI course introduced me to machine learning’s potential, but it was an open-source object detection project that turned theory into action. I spent late nights adjusting code and analyzing results—frustrated yet energized by small wins. That basic system, which identified household objects, now seems simple, but it started my obsession with teaching machines to "see." Grad school let me dig deeper. I focused on computer vision, convolutional neural networks (CNNs), and the math behind detection algorithms. My thesis explored optimizing region-based CNNs for faster performance without losing accuracy—a challenge still critical today. After graduation, I joined a computer vision startup for retail. Here, theory met reality. Academic models struggled with real-world issues: bad lighting, blocked objects, and odd angles missing from standard datasets. My first major project tracked how customers interacted with shelf products. Over six months, we boosted accuracy from 65% to 92% by fixing these real-world problems—proving that iterative work pays off. As the field advanced, I adapted.