The course is for all interested in accessing the deep learning field in a much easy way. Especially, the course is designed for deep learning beginners with only basic knowledge in python and a bit of expertise in data preprocessing and machine learning. The course can also be used for intermediate-level students for a complete review in theory and code practice in three major real-world projects. The course uses new perspectives to guide how to learn deep learning from theory to practice quickly and map each piece of the theory of deep learning into coding practice. The three main projects introduce applying deep learning methods on different tasks in regular tabular data, images (computer vision) and languages/text (NLP).
This course will guide you:
•How artificial neuron is proposed, the basic motivation of artificial intelligence.
•How a neural network is composed and perform computation
•The general structure of a neural network
•The general methods on building a deep neural network
•How classification and regression are performed by neural network
•How to build a neural network on regular tabular data by insurance quote data analysis
•How to build neural work on image data
•How to model image data with convolutional neural network
•How to model sequence/language/text data with recurrent neural network
•How to build the entire pipeline for all neural network models step by step with theory-code mapping demo
•How to implement deep neural network models in PyTorch, an extremely popular open-source framework that has been enthusiastically embraced by the deep learning community
•How to implement and develop training deep learning models on Google Colab with Free GPU resources
All course code demos are shared through Colab with easy access and reproducibility (A Gmail account is all you need). The code demo mainly focuses on how to use high-level APIs provided by PyTorch and shows you why and how the code maps the fundamental principles. In the code demo, we show you where you should go back to review the relevant theory with vivid snapshots in place.
Even if the demo is presented in a very straightforward way, I highly recommend that you can reproduce all steps by yourself. Slower paces at the beginning will make faster in the future! The code only becomes yours only after you can write them by yourself! Therefore, please make progress step by step without skipping any videos/materials, and be PATIENT!
See you in the class, and I am more than happy to answer your questions and help you along your deep learning journey!
What you’ll learn
•Learn how deep learning REALLY works from theory to REAL-WORLD practice with a vivid demo
•Learn how to link theory with coding practice with easy PyTorch
•Leverage and code deep learning models with Google Colab and GPU.
•Learn how feedforward neural network, convolutional neural network and recurrent neural network work by hands-on step by step code explanation
•Three major projects cover the applications in deep learning from insurance, image recognition and sentiment analysis (NOT toy data)
Are there any course requirements or prerequisites?
•Basic programming knowledge in python(e.g., function, class, list) with a bit of ML related toolbox such as sklearn
•Some math concepts and skills at the high school level. The idea that one derivative is a plus but not mandatory is
Who this course is for:
•Anyone interested in deep learning and its application
•Students who have at least high school knowledge in math and who want to start learning Deep Learning
•Any students in college who want to start a career in Data Science
•Any developers who want to level up in Deep Learning
•Any business owners who want to understand how to leverage the technology of Deep Learning in their business
