Zhen He

Associate Professor

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

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

Building: Beth Gleeson, Room: 235




Research Grants

PhD thesis


Spark related topics


My research interests are in deep learning. I am leading a deep learning research group at La Trobe university. There are currently 5 students in the group working on a number of different projects. We are focused on working three different data types: video, image and text. For video we are working with the Australian Institute of Sport (AIS) on action recognition in a number of different sports. For image we are working with the Alfred hospital on cancer diagnosis from CT scans of lungs. For text we are working with Telstra on improving customer service experiences.

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


I am currently teaching a subject called Big Data Management on the Cloud CSE3/4BDC. 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.

The details of the Big Data Managment on the cloud subject can be found here: CSE3/4BDC

hit counter website
hit counter website