Summary
Bin Zhu is a Research Assistant and Ph.D. candidate in Electrical and Computer Engineering at the University of Delaware with 14 years in research and five years focused on applied machine learning and deep learning for vision tasks. He designs and implements CNNs, RNNs, LSTMs, attention and transformer-based models for image processing, object and emotion recognition, video engagement classification, event detection, and driver gaze estimation. Proficient in TensorFlow, PyTorch, Caffe, OpenCV, Scikit-Learn and languages including Python, R, Matlab and SQL, he blends classical ML (SVM, XGBoost, KNN) with modern deep architectures. Known for translating academic rigor into practical systems, he often tackles multimodal and temporal problems that require both sequence modeling and spatial feature learning. Based in Newark, Delaware, he brings a research-first mindset to solving real-world perception challenges and mentoring collaborators across interdisciplinary projects.
13 years of coding experience
Doctor of Philosophy (Ph.D.), ECE, Doctor of Philosophy (Ph.D.), ECE at University of Delaware