Deep learning, a subset of artificial intelligence, has revolutionized industries worldwide, from healthcare to finance. In today's technological landscape, a comprehensive understanding of deep learning is essential for students pursuing careers in computer science and electrical and computer engineering. The course "Deep Learning" is designed to provide senior-level undergraduate students with the technical and entrepreneurial skills necessary to succeed in these fields.

Throughout the course, students will explore the underlying principles of deep learning. The course will cover basic concepts such as neural network architectures, optimization algorithms, and regularization techniques. Students will also learn about more advanced topics such as convolutional neural networks, recurrent neural networks, deep reinforcement learning, generative adversarial networks, and distributed and federated learning. Additionally, the course will cover the practical applications of deep learning in various fields, such as image and speech recognition, natural language processing, and autonomous vehicles.

This course integrates hands-on projects and case studies to instill an entrepreneurial mindset (EM) in students while providing them with a solid foundation in deep learning. By working on these practical applications, students will learn to identify opportunities for value creation across various contexts, manage risk, persist through failures, and collaborate effectively. They will also acquire the skill to draw connections between disparate fields such as computer science and healthcare, or electrical and computer engineering and energy management. Upon completion, students will be well-equipped with the technical expertise and entrepreneurial acumen to make impactful changes in diverse industries. This holistic approach prepares them for thriving careers in modern engineering fields like data science and artificial intelligence, as well as further graduate studies.

Entrepreneurial Mindset Integration: The course incorporates the EM throughout, showcased through the following EM map indicating its integration into lecture discussions, hands-on activities, and projects. Hyperlinks are provided for easy access to materials with explicit EM activities, empowering students to identify opportunities and create value in deep learning applications.

EM Map (updated July 2023):

1. Lecture Discussions: DeepLearningSignalProcessingH4.pdf (in Course Resource at the bottom of the page)

Hands-on Activities: Convolutional Neural Networks in course GitHub repository: https://github.com/ProfessorDong/Deep-Learning-Course-Examples/tree/master/CNN_Examples

EM Projects:

• Perception system of autonomous vehicles: 

https://github.com/ultralytics/yolov5, https://github.com/pierluigiferrari/ssd_keras, https://github.com/prophesee-ai/prophesee-automotive-dataset-toolbox

• Medical imaging:

https://github.com/jakeret/unet, https://github.com/ellisdg/3DUnetCNN

• Industrial inspection:

https://github.com/donrax/industrial-surface-inspection-datasets

2. Lecture Discussions: DeepLearningSignalProcessingH5.pdf (in Course Resource)

Hands-on Activities: Recurrent and Attention-based Neural Networks in course GitHub repository:

https://github.com/ProfessorDong/Deep-Learning-Course-Examples/tree/master/RNN_Examples 

EM Projects:

• Transformers for natural language processing and computer vision:

https://github.com/huggingface/transformers

• AI in Finance: https://github.com/AI4Finance-Foundation/FinGPT 

3. Lecture Discussions: DeepLearningSignalProcessingH6.pdf and DeepLearningGeneraitveModel.pptx (in Course Resource)

Hands-on Activities: Generative AI in course GitHub repository:

https://github.com/ProfessorDong/Deep-Learning-Course-Examples/tree/master/GAN_Examples  

EM Projects:

• Neural rendering for 3D model generation:

https://github.com/nerfstudio-project/nerfstudio, https://docs.nerf.studio/, https://github.com/NVlabs/instant-ngp 

4. Lecture Discussions: DeepReinforcementLearning.pptx (in Course Resource)

Hands-on Activities: Deep Reinforcement Learning in course GitHub repository:

https://github.com/ProfessorDong/Deep-Learning-Course-Examples/tree/master/DRL_Examples

EM Projects:

• AI in drug discovery and biology:

https://github.com/deepchem/deepchem, https://deepchem.io/, https://github.com/isayev/ReLeaSE, https://github.com/MolecularAI/Reinvent 

5. Hardware Implementation: Implementation.pptx (in Course Resource)

NVIDIA Jetson Nano: https://developer.nvidia.com/embedded/jetson-nano-developer-kit 

Intel Movidius Neural Compute Stick and OpenVINO: https://www.intel.com/content/www/us/en/developer/articles/news/intel-neural-compute-stick-2-and-open-source-openvino-toolkit.html?wapkw=neural%20compute%20stick