The implementation of deep learning techniques developed in the field of artificial intelligence is expected to bring revolutionary advancement in biological research and healthcare. This course uses a project-based learning approach to introduce the students to AI techniques, including fundamental concepts such as supervised and unsupervised learning, practical workflows such as model training and benchmarking, and state-of-the-art neural network architectures such as convolutional neural networks and transformer learning. The students will gain practical knowledge when learning to apply AI tools to real-world problems in the field of biology and healthcare, spanning topics including (1) mining the biological big data such as biological sequences, structures, and images, (2) AI-guided clinical decision-making processes such as triage and diagnosis, and (3) AI-guided drug screening. For each project, the course will explain the logic behind the analytic workflow and provide hands-on instructions on optimizing and interpreting AI models. Ethical considerations and challenges, including data privacy, bias mitigation, and the societal impact of AI technologies, will also be discussed.