Artificial Intelligence and Machine Learning are the hottest topics in recent years and attract a lot of attention from researchers in various disciplines. Although enormous high-quality AI/ML courses and tutorials are available online, most of those materials are covering topics in CV and NLP only. Only a handful of courses are focusing on applying cutting-edge AI technology in other disciplines, such as astronomy, computational biology and materialogy. In this AI and ML course series, we will introduce the basic knowledge of AI/ML as well as their implementation details in multidiscipline. More importantly, we will take advantage of the most powerful supercomputer in Australia to boost your own AI applications.
In computational biology, we will talk about how to use linear regression to predict the total vaccinated population; and how to build a Support Vector Classifier to distinguish fake news; how to build a simple CNN model to predict Transcription Factor’s binding site in single nucleotide resolution.
Date/Time
June 13, 2023
Prerequisites
Having basic programming experience with Python is required. Knowledge about using python packages like NumPy, pandas and scikit learn is advantageous. Know basic theory of Machine Learning and Deep Learning and have intentions to use AI/ML and supercomputers to boost their research.
ARE: ARE User Guide
Recommend Materials
Course lectures:
Basic of ML: “Machine Learning” by Andrew Ng
Basic of TensorFlow: “DeepLearning.AI TensorFlow Developer Professional Certificate” by Laurence Moroney
Books:
“Deep Learning” by Ian Goodfellow, Yoshua Bengio and Aaron Courville
“Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow (second edition)” by Geron
Objectives
This course series is designed to help researchers to apply AI/ML in multidiscipline and take advantage of the supercomputer (Gadi) to boost their research. Therefore, it aims to help attendees:
Understanding the basic of AI/ML
Understanding the strength and weakness among different methods
Understanding how to apply basic ML/DL techniques
Understanding how to use Gadi
Learning Outcomes
Know when to use ML/DL
Know popular ML methods: linear regression, SVM, random forest and k-means clustering
Know popular DL methods: DNN, CNN, RNN and Transformer
Know how to formulate problems in Computational Biology (such as medical image segmentation, nanopore sequencing and protein binding sites prediction)
Know how to use python machine learning package: Scikit learn
Know how to use python deep learning platform: Tensorflow
Know how to setup python environment in Gadi
Know how to distribute model training in Gadi
Overview
Content Tools