AI for Scientific Research 專項課程

This course will teach you how to leverage the power of Python and artificial intelligence to create and test hypothesis. We'll start for the ground up, learning some basic Python for data science before diving into some of its richer applications to test our created hypothesis. We'll learn some of the most important libraries for exploratory data analysis (EDA) and machine learning such as Numpy, Pandas, and Sci-kit learn. After learning some of the theory (and math) behind linear regression, we'll go through and full pipeline of reading data, cleaning it, and applying a regression model to estimate the progression of diabetes. By the end of the course, you'll apply a classification model to predict the presence/absence of heart disease from a patient's health data.

This course is aimed at anyone interested in applying machine learning techniques to scientific problems. In this course, we'll learn about the complete machine learning pipeline, from reading in, cleaning, and transforming data to running basic and advanced machine learning algorithms. We'll start with data preprocessing techniques, such as PCA and LDA. Then, we'll dive into the fundamental AI algorithms: SVMs and K-means clustering. Along the way, we'll build our mathematical and programming toolbox to prepare ourselves to work with more complicated models. Finally, we'll explored advanced methods such as random forests and neural networks. Throughout the way, we'll be using medical and astronomical datasets. In the final project, we'll apply our skills to compare different machine learning models in Python.

In this course, we will build on our knowledge of basic models and explore advanced AI techniques. We’ll start with a deep dive into neural networks, building our knowledge from the ground up by examining the structure and properties. Then we’ll code some simple neural network models and learn to avoid overfitting, regularization, and other hyper-parameter tricks. After a project predicting likelihood of heart disease given health characteristics, we’ll move to random forests. We’ll describe the differences between the two techniques and explore their differing origins in detail. Finally, we’ll complete a project predicting similarity between health patients using random forests.