ODSC APAC Talks
--Wednesday, 7th September
-Thursday, 8th September
ODSC APAC Tutorials&Workshops
--Wednesday, 7th September
-Thursday, 8th September
--Wednesday, 7th September
-Thursday, 8th September
--Wednesday, 7th September
-Thursday, 8th September
10:40
- 11:25
Big Data and Artificial Intelligence – Driving Personalised Medicine of the Future
Talk | Big Data Analytics | Machine Learning | Intermediate
In this talk, Fatemeh overviews the main themes in her research program from minimally-invasive biomarker discovery for personalised medicine and single-cell sequencing data analysis to computational drug repositioning and network pharmacology. Across all themes, Dr Vafaee’s research heavily relies on multidisciplinary expertise and cross-faculty collaborations to generate translatable outcomes impacting upon biomedicine of the future…more details
10:40
- 11:25
MLOps for Musicians
Talk | Big Data & Data Analytics | All Focus Areas | All Levels
How far can we take democratization of data and AI? As an eccentric progression of my quest to answer this question, I currently work at Qosmo, Inc. whose mission is to advance human creativity with AI. In this talk I will talk about AI for music. In recent years, there has been some remarkable progresses in AI for music and I will cover these developments in summary of the recent white paper I published. It may not be a surprise to find out that musicians are not the most technical users. We therefore released Neutone, an AI audio plugin & community, in the aim of bridging the gap between AI research and musical creativity…more details
10:40
- 11:10
Introduction to WSL2 for Data Science with Z by HP
Demo Talk | Machine Learning | All Levels
This introductory session aims to provide answers to these questions, get you introduced to WSL2 and get you started by configuring your machine and running your first code…more details
11:20
- 11:50
Azure Machine Learning with Kubernetes Anywhere
Demo Talk | All Levels
Azure Machine Learning Kubernetes extends AzureML service capabilities seamlessly from Azure cloud setting to any infrastructure across on-premises, multicloud, and the edge. As an attached compute target in Azure Machine Learning platform, Kubernetes compute enables you to run training jobs or to deploy models as online/batch endpoint in user-managed Kubernetes cluster anywhere…more details
Chenlu Jiao
Product Manager | Microsoft
11:35
- 12:20
Responsible AI Starts with Responsible Design
Talk | Responsible Ai | Intermediate
The desire to embody Responsible AI practices requires an understanding of, the context around, and the impact on the end user. To achieve this, design and research are just as pivotal to the RAI conversation as ML. There is no bigger risk, and no greater irresponsibility, than to not interface with those who will be affected by your design. In this talk, Bujuanes Livermore will share how she navigates customer relationships to encourage end user contact and how this process can help mitigate assumptions and therefore risk. She will also recommend next steps for when that first conversation meets with too much resistance, as well as how to navigate those waters effectively and professionally through designing experiments and highlighting risks in an assumptions grid. Learn some of the lessons and ‘stealth mode’ tactics in designing that conversation with the client from one of the leaders in the field, the Head of Research & Design in Data, Intelligence & Design at Microsoft with over 15 years of experience…more details
11:35
- 12:20
Annotated Data: The Bedrock of Successful AI Deployments
Talk | Machine Learning | Deep Learning | All Levels
In this talk, I am going to highlight some of the best practices around data annotation and ML DataOps that help companies quickly develop, deploy and continuously update their ML models…more details
11:35
- 12:20
Key Performance Indicators, Visualisation Techniques and Interpretability for ETA (Estimated Time of Arrival) Prediction Models
Talk | Machine Learning | Big Data Analytics | Intermediate
Apart from the performance , interpretability part kicks in when there is a change in the prediction by model in between the journey of an object. The most anticipated and important question is “What are the reasons the prediction was changed from x to y in the middle of the journey?”. Not able to provide reasons and answers to the questions above could easily lead to loss of trust in the system. In this talk, you will learn about different KPIs, visualisation techniques that can capture the behaviour of ETA models. We will also walk through why it is important to have interpretable model by design to be able to answer some of the questions…more details
12:00
- 12:30
Leveraging HPCC Systems Platform for Machine Learning Applications
Demo Talk
In this session, we will be walking through the way that RVCE-HPCC Systems Centre of Excellence on Cognitive Intelligent Systems for Sustainable solutions have leveraged HPCC Systems for Big Data analysis. Demonstration and visualization of few applications such as Analysis of corvid 19 data, Analysis, Classification of Surface water will be showcased for the audience to understand various components involved in the architecture of HPCC Systems. We intend to discuss the comparison with other distributed platforms such as Hadoop to show the applicability of HPCC Systems platform to solve big data problems…more details
12:30
- 13:15
Generating Product Descriptions and Answers for Customer Queries on E-commerce Platforms
Talk | NLP | Machine Learning | Intermediate
In this talk, I will present two applications on one of the most popular e-commerce platforms: Amazon. We will first look at generating product descriptions, and show how we train a multimodal model that takes product images and metadata as input to generate descriptions for 23 product types. Although we found that the generated descriptions are fluent and persuasive, they are not always faithful (i.e. the details are not real)…more details
12:30
- 13:15
Data Science in a Data Driven Energy Organisation
Talk | MLOps & Data Engineering | Big Data Analytics | Beginner
In this talk, we will demonstrate how we process our Big Data, gain insights of our Smart Grid and Innovation applications, how we do detect faults from smart meter power quality data and meter channel alerts that resulted in reducing shock incidents in our network, how we automate monitoring of customer sites for immediate hazard detection, how we balance the grid from distributed energy resource management system, and how we automate fault detection analytics and jobs dispatch with no human intervention…more details
12:30
- 13:15
Data-efficient Active Testing of Machine Learning Models
Talk | MLOps & Data Engineering | All Levels
Machine learning models are being deployed extensively in many important areas to assist humans in making important decisions. But there is no guarantee a model will always perform well after deployment as its developers intended. Understanding the correctness of a model is thus crucial to prevent potential failures that may have a significant detrimental impact in critical application areas. In this talk, I will discuss the challenges we face to ensure the correctness of deployed machine learning models and introduce some works on how to efficiently test a machine learning model using only a small amount of labelled test data.
12:30
- 13:15
Analyzing Blockchain Data to Detect Illicit Transactions made Using Bitcoin
Talk | Machine Learning | Deep Learning | All Levels
In this talk Rohan will take you through how clustering and transaction times series fingerprinting can give insights into the underlying transaction behaviour of users and help find the criminals utilizing the bitcoin network for illicit activities..more details
Rohan Maheshwari
Student | RV College of Engineering
13:45
- 14:30
Sentiment Analysis and Aspect-based SA and Beyond
Talk | NLP | Machine Learning | Intermediate
This talk is for those who want to learn the introduction of sentiment analysis task and its different model choices to implement it. By listening this talk, you will become familiar and comfortable with the sentiment analysis and its different methodological approaches. Plus, I will bring up more advanced topics in this area such as issues and challenges in sentiment analysis or Aspect-based Sentiment Analysis (ABSA)…more details
13:45
- 14:30
Explainable Machine Learning – A Human Centric Perspective
Talk | Responsible Ai | Beginner-Intermediate
Machine Learning and AI models are often considered as black boxes, and the lack of transparency in the working of these models lead to lack of trust and adoption. In order to promote end user trust Explainable AI (XAI) and model explainability techniques like LIME, SHAP are widely used. But are these methods really human friendly? Do we have any existing method or framework that can provide explainability to non-technical users? How can we use XAI to bridge the gap between AI and end users to promote AI adoption?…more details
14:40
- 15:25
The Future of AI and Machine Learning
Talk | Machine Learning | All Focus Areas | All Levels
As Gartner notes in the “State of Data Science and Machine Learning” report, DSML platforms are now addressing two growing and equally important markets: (i) A ‘multipersona’ market with a central focus on time to value, ease of use, and collaboration between multiple technical and nontechnical personas, and (ii) an ‘engineering’ market focused on primarily technical personas whose primary aim is to engineer (design, develop, deploy, monitor, and maintain) scalable, enterprise-wide AI solutions…more details
14:40
- 15:25
Responsible AI: The New Frontier of Ethics in Technology
Talk | Responsible AI | All Levels
In this presentation, I’ll go through more about ethical and responsible AI, why we need it, major concerns to consider, some of the most recent discoveries and how they impact the future of technology…more details
15:05
- 15:35
Real-time Analytics, AI&Apps with Deephaven Data Labs
Demo Talk | All Levels
This demonstration of Deephaven will show you how to: 1. Launch Deephaven from Jupyter and your Python IDE. 2. Access and manipulate Kafka and Parquet with just a few lines of code. 3. Filter, aggregate, join, select, and project ticking, updating tables in real-time. 4. Create and interact with table and plot widgets in web dashboards and Jupyter. 5. Integrate Deephaven with matplotlib, PyTorch, and other popular tools.
15:35
- 16:20
Real-time Data Science Made Easy
Talk | Machine Learning | Deep Learning | All Levels
In this talk, we will explore production-quality, real-time data science using the current leading open, real-time technologies: Kafka, redpanda, ksqlDB, Materialize, and Deephaven Community Core…more details
15:35
- 16:20
Image Generation with GANs
Talk | Deep Learning| Intermediate
This talk will introduce you to the world of Generative Models through the GAN lens. We will discuss how a simple game of adversaries leads to such powerful models. We will cover the evolution and advancement in the architecture of GANs along with some exciting use-cases. Towards the end we will go through a quick hands-on to generate images with GANs ourselves…more details
15:35
- 16:20
Using Augmented Reality, Machine Vision & Deep Learning for Solving Supply Chain Problems
Talk | Deep Learning | Intermediate
The Fourth Industrial Revolution (Industry 4.0) is the ongoing automation of traditional manufacturing and industrial practices, using modern smart technology. Large-scale machine-to-machine communication (M2M), the internet of things (IoT), Augmented Reality, Machine Vision, and Deep Learning are integrated for increased automation, improved communication and self-monitoring, and the production of smart machines that can analyze and diagnose issues. Designing a humanless system sometimes poses the biggest risk if something goes wrong. This is where Augmented Reality will add the human into the automation loop in the world of Automation…more details
15:35
- 16:20
Monitoring CV Systems: A Unique Solution to a Unique Problem
Talk | MLOps & Data Engineering | Intermediate
In this talk, Ray Reed will explore the plethora of problems impacting data and model health for computer vision systems specifically, and construct an approach for detecting, debugging, and reacting to these issues at scale. In the case of tabular data, powerful monitoring capabilities can be achieved by collecting telemetric data such as missing value ratios, cardinality of discrete features, descriptive statistics, etc. For image and video data, however, metrics of interest must be derived…more details
15:45
- 16:15
The Hidden Layers of Tech Behind Successful Data Labeling
Demo Talk | All Levels
In this session, attendees will learn how iMerit is solving the problem of scaling data pipelines with accuracy using unique technology. Join iMerit’s VP of Product, Glen Ford, as he uncovers the invisible technology building successful data labeling workflows and discovering anomalous and novel classes for customers using iMerit’s Edge Case technology…more details
11:50
- 12:50
Microsoft’s Accelerator for MLOps
Workshop | MLOps & Data Engineering | Machine Learning | All Levels
MLOps means different things to different people, however, the fundamental essence of MLOps is to deliver models into productions faster with a consistent, repeatable and reliable approach. Based on our experience of working with various large and small customers across the world, Microsoft has developed an accelerator to do exactly what the word suggests – accelerate our customer’s journey to production. Simplicity and segregation of duties are key pillars of this accelerator, which means that our intention is that Data Scientists, ML Engineers and IT teams don’t need significant upskilling before they can do MLOps…more details
13:30
- 14:30
Key Design Principles for the Modern Data Engineering Stack
Workshop | MLOps & Data Engineering | Intermediate
In this talk, I take you through key design principles to think about when designing your data platform. I use a data platform design pattern that I have implemented for Blike, a FinTech startup specialising in cycle-to-work schemes, to demonstrate that less is more…more details
13:30
- 14:30
Advanced NLP: Deep Learning and Transfer Learning for Natural Language Processing
Workshop| NLP | Intermediate-Advanced
Being specialized in domains like computer vision and natural language processing is no longer a luxury but a necessity which is expected of any data scientist in today’s fast-paced world! With a hands-on and interactive approach, we will understand essential concepts in NLP along with extensive hands-on examples to master state-of-the-art tools, techniques and methodologies for actually applying NLP to solve real-world problems. We will specifically be focusing on deep learning and deep transfer learning models to learn and solve popular tasks using NLP including NER, Classification, Search / Information Retrieval, Summarization, Classification, Language Translation, Q&A systems…more details
14:40
- 15:40
Use of Transfer Learning in Computer Vision
Tutorial | Machine Learning | Beginner-Intermediate
This session focuses on transfer learning and it’s uses in various computer vision applications. The attendees would get an overall understanding of the difficulties in training a CNN model from scratch, use of transfer learning techniques and pre-trained models…more details
14:40
- 15:40
Interpretable AI : Making Black Box Models Explainable
Tutorial | Machine Learning | Responsible Ai | Intermediate-Advanced
The wider goal of Ai is to gain knowledge, but many problems are solved with big datasets and black-box machine learning models. The model itself becomes the source of knowledge instead of the data. Interpretability makes it possible to extract this additional knowledge captured by the model. Humans most of the time usually do not ask why a certain prediction was made, but why this prediction was made instead of another prediction. We tend to think in counterfactual cases, i.e. “How would the prediction have been if input X had been different?”. For a house price prediction, the house owner might be interested in why the predicted price was high compared to the lower price they had expected. If my loan application is rejected, I do not care to hear all the factors that generally speak for or against a rejection. I am interested in the factors in my application that would need to change to get the loan. I want to know the contrast between my application and the would-be-accepted version of my application…more details
15:50
- 16:50
Route Optimization using Reinforcement Learning and Metaheuristics
Workshop | Deep Learning | MLOps & Data Engineering | Intermediate-Advanced
The current era is driven by eCommerce platforms and the COVID pandemic gave rise to the need for home delivery. The end consumers have multiple options to cater for their needs and in that case, the eCommerce platforms have to provide on-time and quality delivery to stay ahead in the market and at the same time boost their profit margins. Route Optimization is one of the most critical aspects of planning and transportation as it ensures that deliveries always arrive on time and carry out the same with the lowest possible cost and energy consumption. However, there are a lot of variables that eCommerce platforms need to consider in a real-time scenario…more details
Select date to see events.
