Zhen He

Associate Professor

Department of Computer Science and Computer Engineering
La Trobe University
Bundoora, Victoria 3086
Australia

Tel : + 61 3 9479 3036
Email: z.he@latrobe.edu.au

Building: Beth Gleeson, Room: 235
 


Home

Biography

Publications

Research Grants

PhD thesis

Teaching

Spark related topics



Research

My research interests are in deep learning and AI. I lead a deep learning research group at La Trobe university. There are currently 7 students/research assistants in the group working on several different projects. We are focused on working with three different data types: video, text and images. For video we are working with the Australian Institute of Sport (AIS) on action recognition and multi-person tracking in several different sports. This has attracted several significant grants. For text we are working with Telstra to develop deep learning solutions that help customer service agents answer customer inquiries more efficiently. The resultant software has been put into production with favorable results. For images we are working with two different organizations. The Centre for Alcohol Policy Research to develop software to classify images of people drinking alcohol. We are also working with department of Agribio at La Trobe and Center of Excellence in Plant Energy Biology at the ANU on various projects that use deep learning to phenotype plants. This will help farmers to use their land more productively.

We also have a project working on distributed deep learning on Apache Spark. The code is completely written in Scala and provides a user friendly way of running distributed deep learning on Apache Spark. It features many common deep learning algorithms such as 2D and 3D convolutional neural networks, auto encoders, fully connected layers, sparse coding, optimization algorithms like adagrad, momentum, etc. We are researching on various ways of minimizing communication costs during the training of distributed models.

List of Research Interests

  • Deep Learning
  • Computer Vision
  • Text mining
  • Big Data using Apache Spark

Getting Started with Deep Learning Workshop

We are running the deep learning workshop again on Monday the 14th of Oct 2019 at our La Trobe city campus. We have been running this workshop for more than 3 years. It has received a lot of positive feedback. We are constantly updating the material due the rapid changes in the deep learning field.

In the workshop we will dispel the myth that deep learning can only be understood by the experts. We will start from the basics to equip the students with all the necessary knowledge to understand the state-of-the-art deep learning algorithms and architectures. The students will be taught how convolutional and recurrent neural networks can be applied to solve many different practical problems.

Please click the following link to get more information including registration information. Getting started with Deep Learning Workshop Information

Teaching

I am currently teaching a subject called Big Data Management on the Cloud CSE3/5BDC. This subjects goes into substantial depth into the Hadoop Ecosystem. It both teaches students how to program in the Hadoop Ecosystem and expose students to the system architectures underneath. It also covers a lot of the most popular services offered by Amazon Web Services (AWS). Students gain hands on experience programming Hadoop and Amazon Web Services.






hit counter website
hit counter website