Machine Learning Student Seminars
Do you find yourself wondering what great research is being done in our group? Our ML Student Seminar series is intended to give us all a chance to see and hear about what others work on and thereby gives the chance to identify where collaboration is possible. For the students, this is a great chance to present their work and get some feedback and ideas.
In every session, a PhD (or postgrad) student will give a talk on her current work. We will then give feedback, discuss potential problems the student is facing, provide ideas on how to solve challenges and let our creativity flow. The talks are not intended to be perfect and could be quite short. However, the student needs to provide us all with enough information to understand the research and the particular problem she is aiming to solve.
Where and when?
The ML Student Seminars will be held bi-weekly (alternating with the AI Reading Group!) on Thursdays 2pm-3pm in 303S-561. We strongly encourage all members of our group to participate – students and lecturers.
Speakers
In order to have an interesting seminar series, we aim for diverse talks and therefore iterate through supervisors. The supervisors will be asked to nominate students that should give a talk soon — preferably new students that still search for their path, students struggling with a specific problem, but also students that already have a lot of interesting research to report. Please avoid nominating students that just had their Provisional Year Reviews as many of us will already have seen their current work. Since we meet bi-weekly, every student will be presenting about once a year.
ML Student Seminar on Dec 2 2021: Adversarial Learning on Time Series Forecasting
Where and when: Thursday, Dec 2 at 2-3pm in Google Meets (see the calendar invitation for the link) Speaker: Mark Chen, supervised by Joerg Wicker and Gill Dobbie Abstract: Time series forecasting is one of the main topics which involves time series data. It predicts the future values based on previously observed values of the time series. However, the robustness of time series forecasting...
ML Student Seminar on Nov 18 2021: Beyond Recall: Teaching High Quality Language Models to Generalise to Unseen Compositional Questions
Where and when: Thursday, Nov 18 at 2-3pm in Google Meets (see the calendar invitation for the link) Speaker: Tim Hartill, supervised by Michael Witbrock and Pat Riddle Abstract: Sequence-to-sequence Transformer-based Language Models pretrained on large text corpora have shown impressive ability to memorise and recall singular facts. However, an ability to reason over facts learned in...
ML Student Seminar on Nov 4 2021: New Zealand Bat Audio Analysis
Where and when: Thursday, Nov 4 at 2-3pm in Google Meets (see the calendar invitation for the link) Speaker: Tsz Fung Ip (Roy), Master of Data Science student Abstract: Due to urbanization in the past few decades, various species of bats in New Zealand are facing serious threats, even extinction. In order to learn more about bat allocation and their behaviour, frequency analysis on the audio...
ML Student Seminar on Oct 21 2021: Understanding the mechanisms of multiple epidemic waves of COVID-19
Where and when: Thursday, Oct 21 at 2-3pm in Google Meets (see the calendar invitation for the link) Speaker: Johnny Zhu, supervised by Joerg Wicker and Gill Dobbie Abstract: Covid-19 has been raging around the world for more than 20 months. The epidemic has occurred repeatedly in many countries, including New Zealand, also known as multiple epidemic waves or subepidemics. Data scientists...
ML Student Seminar on Sep 23 2021: Machine learning application in thin-walled structures
Where and when: Thursday, Sep 23 at 2-3pm in Google Meets (see the calendar invitation for the link) Speaker: Arthur (Zhiyuan) Fang, supervised by Dr. Krishanu Roy and Dr. James Lim in the Department of Civil and Environmental Engineering Abstract: Structural behaviour analysis of thin-walled structures is one of the major concerns of civil engineering/construction engineering. The...
ML Student Seminar on Sep 9 2021: Machine Learning in Julia
Where and when: Thursday, Sep 9 at 2-3pm in 303S-561 Speaker: Anthony Blaom, https://ablaom.github.io Abstract: Julia is a young but mature programming language which allows one to write fast code fast. Over a two year period, we have developed a Julia toolbox, called MLJ, for training, evaluating, tuning, and composing a large number of machine learning models written in Julia and other...
ML Student Seminar on Aug 26 2021: Hitting the Target: Stopping Criteria for Active Learning
Where and when: Thursday, Aug 26 at 2-3pm in 303S-561 Speaker: Zac Pullar-Strecker, B.Sc. Student and Research Assistant (for Joerg Wicker) Abstract: Training modern ML models frequently requires large datasets which are expensive and time-consuming to collect. Active Learning addresses this by providing a method to train models with smaller amounts of labeled data. However, the lack of data...
ML Student Seminar on Aug 12 2021: Reinforcement Learning Control for Vapour Compression Refrigeration System
Where and when: Thursday, Aug 12 at 2-3pm in 303S-561 Speaker: Tech Logg Ding, Ph.D. student, Department of Mechanical Engineering Abstract: Refrigeration systems are essential for various cooling applications in modern society. The majority of the refrigeration systems in the world uses the Vapour Compression Refrigeration Cycle (VCRC) technology due to its’ efficiency. In the literature,...
ML Student Seminar on July 29 2021: SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words
Where and when: Thursday, July 29 at 2-3pm in 303S-561 Speaker: Jonathan Kim, PhD student, supervised by Pat Riddle and Joerg Wicker Abstract: Loop closure detection is an essential tool of Simultaneous Localization and Mapping (SLAM) to minimize drift in its localization. Many state-of-the-art loop closure detection (LCD) algorithms use visual Bag-of-Words (vBoW), which is robust against...
ML Student Seminar on July 15 2021: Machine Learning for Detecting Vision Problem in Young Children
Where and when: Thursday, July 15 at 2-3pm in 303S-561 Speakers: Jason Turuwhenua is a Senior Research Fellow and Principal Investigator for the Eye Health and Diagnostics Lab at the Auckland Bioengineering Institute. Jason is interested in the application of engineering techniques to solve problems in the diagnosis of vision. Mohammad Norouzifard is Postdoctoral Research Fellow in Eye Health...
