- Видео 96
- Просмотров 31 374
DARE ARC Centre
Австралия
Добавлен 29 июн 2020
Selected DARE Centre seminar series presentations and online conferences.
Navigating Multimodal Data in Geosciences: From Large-Scale Geophysical Datasets to Hand Specimens
Abstract:
Since the early days of analysing digital images, researchers have tried to automatically extract meaning from the images by both enhancing them for better interpretation by the human eye and brain and by automatically extracting features from the images themselves. One of the drawbacks of using feature extraction methods that search for specific shapes (e.g. lineaments) in natural scenes such as geophysical data is that geological datasets are complex and do not follow simple rules. Additionally, different features across multimodal datasets (e.g. gravity and magnetics) may correspond to the same underlying geology.
What if we adopt an alternative approach by segmenting and organ...
Since the early days of analysing digital images, researchers have tried to automatically extract meaning from the images by both enhancing them for better interpretation by the human eye and brain and by automatically extracting features from the images themselves. One of the drawbacks of using feature extraction methods that search for specific shapes (e.g. lineaments) in natural scenes such as geophysical data is that geological datasets are complex and do not follow simple rules. Additionally, different features across multimodal datasets (e.g. gravity and magnetics) may correspond to the same underlying geology.
What if we adopt an alternative approach by segmenting and organ...
Просмотров: 41
Видео
Revolutionising Materials Science with Large Language Models: A New Paradigm in Material Discovery
Просмотров 2,9 тыс.Месяц назад
Abstract: This seminar explores the transformative potential of Large Language Models (LLMs) in revolutionising the development of advanced materials. By comparing LLMs with conventional machine learning techniques, we highlight their unique capabilities in multi-task learning, processing and generating predictions in universal formats, and leveraging vast amounts of text data to address comple...
Three Ways of Thinking About ENSO
Просмотров 2,5 тыс.2 месяца назад
Abstract: El Niño-Southern Oscillation (ENSO), the phenomenon that gives rise to El Niño and La Niña events, has long been a subject of study by applied mathematicians. This phenomenon is a quasi-periodic oscillation between El Niño (warm) and La Niña (cool) events which occur every 2-7 years via air-sea coupled processes in the ocean and atmosphere of the equatorial Pacific. These events, by p...
Opportunities for Sustainability with Multiscale Minerals Value Chain Integration
Просмотров 1,3 тыс.3 месяца назад
Abstract: Recent advances in sensing have augmented ore discovery, mining and sorting procedures that promise to improve the effectiveness and sustainability of mining operations. While these activities operate at different spatial and temporal scales, combining posterior models can further benefit the sustainability of exploration and mining operations. Discovering the combination of data and ...
Regional Geophysical Data Analysis in 2D and 3D
Просмотров 1,9 тыс.4 месяца назад
Abstract: Regional geophysical datasets underpin our ability to build 2D and 3D geological models across much of the world, where surface expressions of geology are limited. In this talk we will explore the range of methods from purely interpretive to Machine Learning that are currently used to build geological models. We will primarily focus on airborne magnetic data sets, however the logic ap...
Analysing Data Summarised as Distributions - DARE Symposium 2024
Просмотров 1894 месяца назад
Keynote by Professor Scott Sisson - DARE Symposium, February 2024 Abstract: Much of the research that is generated by Universities and Research Centres is driven by PhD students. In this presentation I will showcase some of the work done by some of my recent PhD students as part of their thesis. These vignettes will focus on research in “symbolic data analysis”, which aims to perform statistica...
Revealing Causal Information from Data - DARE Symposium 2024
Просмотров 2434 месяца назад
DARE Chief Investigator Presentation by A/Prof Tongliang Liu DARE Symposium February 2024 Abstract: Many tasks in sciences or engineering require the underlying causal information. Since it is typically expensive and time-consuming to conduct randomised experiments, there has been significant attention towards revealing causal relations through the analysis of purely observational data, commonl...
Improving our Understanding of the Impacts of Climate Change on Water Resources Systems
Просмотров 1744 месяца назад
DARE Chief Investigator Presentation by A/Prof Fiona Johnson DARE Symposium February 2024 Abstract: Climate change is expected to adversely impact human and natural water systems. In this presentation I will summarise some of our recent research that aims to improve our understanding of these changes using a mix of data-driven and process-based approaches. In our work we leverage the opportunit...
Bayesian Variable Selection for Spatial-Temporal Quantile Regression - DARE Symposium 2024
Просмотров 1464 месяца назад
10 Minute Thesis Presentation by DARE PhD Candidate, Dilani Kaveendri DARE Symposium February 2024 Dilani is a graduate of Bachelor of Science in Statistics and Operations Research (SOR) Honours Degree who obtained a G.P.A of 3.83 /4.00 thereby being the second academic performer of SOR batch at University of Peradeniya, Sri Lanka. Previously worked as an Assistant Lecturer in the Data science ...
Deep Dive: Leveraging Deep Learning for Deep-Sea Biota Identification in the Great Barrier Reef
Просмотров 3265 месяцев назад
10 Minute Thesis Presentation by DARE PhD Candidate, Ratneel Deo DARE Symposium February 2024 Ratneel is a DARE PhD candidate studying geophysical modeling at the University of Sydney with a research interest in creating a synergy of optimization and inference methods. Prior to that, he completed his MSc in 2018 at the University of the South Pacific, majoring in Computing Science. In his postg...
Ecological forecasts of fauna species response to fire, drought and heatwaves - DARE Symposium 2024
Просмотров 565 месяцев назад
10 Minute Thesis Presentation by DARE PhD Candidate, Vihanga Gunadasa DARE Symposium February 2024 In 2019, Vihanga graduated from the University of Sri Jayewardenepura (USJ), Sri Lanka with First Class Honours in Statistics, securing the third place in her cohort. She also holds an Honours Bachelor’s degree in Quantity Surveying (2018) from Birmingham City University, United Kingdom with a Sec...
Data Management Plans: Considering the FAIR and CARE Principles
Просмотров 6795 месяцев назад
Abstract: This presentation will comment on the importance of data management plans in supporting the management of data created by a research project. It will describe how the FAIR and CARE principles can be applied and used within a data management plan. Discussion on why FAIR and CARE should be considered for the management of data will be presented. A data management plan is a document that...
Second-order Optimization Methods for Machine Learning
Просмотров 6125 месяцев назад
Abstract: First-order optimization methods, particularly stochastic gradient descent, are the primary workhorse in machine learning (ML) for their historically low per-iteration costs. Recent theoretical advancements, including rapid convergence in overparameterized scenarios, implicit regularization, and the emergence of network architectures like skip connections, have solidified their domina...
The Eratos Platform - A Tool to Assist with Research and Commercialisation
Просмотров 3407 месяцев назад
Abstract: Dr Tom Remenyi will present his view on the research sector, and some of the key barriers to transforming research outputs into impact. Tom will then present the Eratos platform, a tool designed to assist with data management and analytics, with a particular focus on assisting research teams commercialise research. Tom will show some demonstrations of how the platform is currently bei...
Challenges in Annotating Datasets to Quantify Bias
Просмотров 2388 месяцев назад
Abstract: Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has raised concerns about equity. In response, there has been an increase in research dealing with bias, including studies focusing on quantifying bias...
The Art and Science of Causal Inference
Просмотров 3298 месяцев назад
The Art and Science of Causal Inference
Teaching Computers How to See Rocks - Using Computer Vision Models to Extract Visual Datasets
Просмотров 44410 месяцев назад
Teaching Computers How to See Rocks - Using Computer Vision Models to Extract Visual Datasets
Continent-Scale Groundwater Models: Constraining Flow Pathways Across Eastern Australia
Просмотров 20211 месяцев назад
Continent-Scale Groundwater Models: Constraining Flow Pathways Across Eastern Australia
How Machine Learning Can Cut the Cost of Downscaling Evapotranspiration
Просмотров 38911 месяцев назад
How Machine Learning Can Cut the Cost of Downscaling Evapotranspiration
Hydrological Modelling, Forecasting and Data Post-Processing
Просмотров 431Год назад
Hydrological Modelling, Forecasting and Data Post-Processing
Topics in Data Assimilation with Applications in Hydrology
Просмотров 184Год назад
Topics in Data Assimilation with Applications in Hydrology
Big Data, Big Dreams: How Remote Sensing and Big Data are Changing Our View of the Coast
Просмотров 282Год назад
Big Data, Big Dreams: How Remote Sensing and Big Data are Changing Our View of the Coast
Understanding Algal Blooms in Shallow Waterbodies
Просмотров 200Год назад
Understanding Algal Blooms in Shallow Waterbodies
Maximising the Resilience of Grasslands to Extreme Precipitation, Nutrients and Grazing
Просмотров 153Год назад
Maximising the Resilience of Grasslands to Extreme Precipitation, Nutrients and Grazing
Mind Your Ps and Qs When Analysing Data - DARE Symposium 2023
Просмотров 46Год назад
Mind Your Ps and Qs When Analysing Data - DARE Symposium 2023
Where the Creeks Run Dry or Ten Feet High: Streamflow Prediction in Australian Context - Symposium
Просмотров 72Год назад
Where the Creeks Run Dry or Ten Feet High: Streamflow Prediction in Australian Context - Symposium
Particle Mean-field Variational Bayesian Inference - DARE Symposium 2023
Просмотров 164Год назад
Particle Mean-field Variational Bayesian Inference - DARE Symposium 2023
Advanced Model Selection using Bayesian Inference Algorithms - DARE Symposium 2023
Просмотров 132Год назад
Advanced Model Selection using Bayesian Inference Algorithms - DARE Symposium 2023
Bayesian Variable Selection for Efficient Graph Structure Learning - DARE Symposium 2023
Просмотров 122Год назад
Bayesian Variable Selection for Efficient Graph Structure Learning - DARE Symposium 2023
do you have the code for this
Thanks for your interest! You might want to have a look at the paper by José Padarian here: soil.copernicus.org/articles/5/79/2019/
Great!
Great stuff Tristan!
Hi Guys, This is one of the most relevant videos that I've found that relates to a research project that I'm working on. Would you be able to help me in answering a few questions relating to the topic at hand? I've already liked this video and have subscribed to the channel. If there's anything else that I can do to in return for your help in better understanding how Variational Inference can be augmented with Copulas, please let me know 😊.
I have been living with type 2 Diabetes for over 8 years but all that came to an end after using the natural herbs medication I ordered from Dr IGUDIA on his RUclips channel. All thanks to the great doctor.
great talk! Could you show us your references please?
Jessie is no longer at DARE, and so can't answer via this channel. Perhaps she has an public online presence you could try?
Thanks a lot for sharing this !!
Glad you liked it!
great, thanks for uploading! I'm currently writing my master thesis about using statFEM for acoustics. This helped a lot!
Glad it was helpful!
Subscribe to our channel for more about our cutting-edge research on data science, mathematics, statistics and AI!