Keynote
Open-source software is at the foundation of machine learning and there are numerous projects supporting various parts of the machine learning lifecycle – from building to deploying and managing models. Join us to learn how Microsoft is investing across open source projects – both by starting new projects, like ONNX Runtime, InterpretML, and FairLearn as well as contributing to existing projects, such as ONNX, DeepSpeed, and PyTorch. We’ll also deep dive into some of our most recent work with PyTorch and share how organizations are using PyTorch on Azure to drive innovation...more details
Keynote
This talk will cover the basics – how graphs are relevant to the problems you need to solve – and how to get started using graph techniques. You’ll learn how to improve your predictions with the data you already have, and how to use graph algorithms and machine learning to find what’s most important in your connected data…more details
Keynote
This talk outlines the CSIRO developed software solutions, which use the latest in cloud architecture, machine learning and distribution channels to support a wide range of digital health applications; from disease gene detection, to personalized gene therapy; from pathogen diagnostics to biosecurity applications. Specifically, we developed novel bioinformatics approaches to track viral evolution that has led to the first study on vaccine efficacy for the different COVID-19 virus strains…more details
Talk | NLP | Intermediate-Advanced
In this talk, I will illustrate the nature and magnitude of the problem, and outline a number of approaches that can be used to train fairer models based on different data settings, without sacrificing overall performance levels. The talk will assume intermediate familiarity with NLP and machine learning methods, and is relevant to all industries…more details
Demo Talk
Analyzing and improving large-scale deep learning model performance is an ongoing challenge that continues to grow in importance as the model size increases. Come learn how to detect and troubleshoot common performance bottlenecks in PyTorch models using state-of-the-art profiling tools….more details
Demo Talk
This demonstration will walk through how an automated decisioning process can accomplish this…more details
Track Keynote | Machine Learning | Deep Learning
Across all this diversity there are some core “intuitions” that form the abstract foundations of their work. In this talk we will cover seven such intuitions or “data science thinking” that a data scientist develops or should aspire to develop to become a more holistic data scientist…more details
Talk | MLOps | Intermediate
We are building a unified AML Kubernetes native agent that will allow you to seamless train ML models on Kubernetes. Supported frameworks include SciKit, TensorFlow , PyTorch and MPI.
The Kubernetes cluster can be AKS in the Azure cloud or it can be on-prem Kubernetes (including Azure Stack Hub, Edge) that you bring to Azure through Azure Arc for Kubernetes. This allows you to centrally manage and govern all your Kubernetes resources in one place and use capacity flexibly for all workloads including AML…more details
Talk | NLP | Intermediate
In this talk, I will discuss both these opportunities and the challenges that we face when working with real-world clinical data, and introduce some of the strategies that we are adopting to make this data more usable, and to model it effectively…more details
Demo Talk
A demonstration of the tools available for developing graph solutions with an emphasis on the Python language and Neo4j graph database. From Jupyter notebooks to Neo4j Desktop come on a journey of development approaches available to the data scientist and software developer alike…more details
Talk | Responsible Ai | Machine Learning | Intermediate
We will deep dive into the tool functionalities by presenting case studies and a live step-by-step demo. Finally, we will conclude with a discussion on future opportunities we are considering on further integrations with other RAI tools, as a quest towards a better integrated RAI ecosystem…more details
Talk | Deep Learning | All Levels
Exploring available open-source reinforcement learning tools and insights on how to go from research to production…more details
Demo Talk
This live talk will demonstrate how Imply can transform streaming data from Kafka to a real-time ML model monitoring application…more details
Talk
This tech talk will cover different approaches from graph feature engineering, from queries and algorithms to embeddings, and how to generate representations of graph using procedures provided in Neo4j Graph Data Science package to generate graph embeddings, ML models for link prediction or node classification, and apply these models to add missing information to existing data…more details
Track Keynote | Machine Learning
This talk will be a case study driven conversation through the delivery of an advanced computer vision edge AI/ML for dynamic, complex and harsh work environments…more details
Talk | Data Analytics
Ravi and Emma is a world first in using AI for audiences to interact with an online documentary using Southern Dialect Auslan. Learn about how Silverpond worked with SBS to develop the concept, train the model and build the web experience…more details
Talk | NLP | Beginner-Intermediate
This session is for those who want to learn the basic introduction of analyzing text data, more advanced NLP handling techniques – word vector, and topic modeling. By completing this session, you will become familiar and comfortable with the basic concepts and techniques for how to start a NLP modeling. Plus, you should be able to understand topic modeling and its commonly used methodologies…more details
Talk
In extreme low data scenarios with few classes, a few shot learning based approach might be challenging to train and evaluate. In these scenarios of low data and low classes with extreme skewness, a fine-grained sub-grouping into finer classes can help stretch the data to more classes simulating natural long tailed distribution…more details
Talk | NLP | Machine Learning | Intermediate
In summarization, the aim is to generate compress, relevant, and concise information from the available data. Different facets of summarization, like document summarization, figure-summarization, microblog summarization, and multi-modal microblog summarization, will be discussed in the talk…more details
Talk
This work focuses on content-based scoring, which aims to quantify the impact of content quality of promotional emails sent across to healthcare practitioners upon the immediate engagement…more details
Talk | Data Analytics
AI ethics does not come in a box. Given the varying values of companies across dozens of industries, a data and AI ethics program must be tailored to the specific business and regulatory needs that are relevant to the company In her talk, Angela will walk through 4 pillars of how to execute Ethical AI for your organization from governance, design, monitoring and education perspectives…more details
Talk | Data Analytics
How do you leverage the Data Science, emerging technology, and talented people to develop a successful, sustainable and scalable Data Science practice? I’ll reveal key insights on how to ensure success, develop the right culture, and avoid common pitfalls…more details
Talk | Machine Learning | Intermediate
In this talk, you will learn about combination architectures that can get your work into production, shorten development time, and provide the performance and scale advantages of an MPP database with the convenience and power of Python. Real use case examples use the open source Vertica-Python project created by Uber with contributions from Twitter, Palantir, Etsy, Kayak and Gooddata…more details
Talk | MLOps and Data Engineering | Advanced
This talk gives a survey on the different techniques for optimizing ML pipelines and lays out trade offs to consider when deploying them…more details
Talk | Data Analytics
AI Singapore has been working on building a system, named Synergos, to support Federated Learning. In this talk, we will present an overview of the key component of Synergos, and zoom into the core component which coordinates multiple parties to train a federated model…more details
Talk | Deep Learning | Beginner-Intermediate
In this talk, we will go into a deeper understanding of the model architecture of vision transformers. Most importantly, we will focus on the concept of self-attention and its role in vision. Then, we will present different model implementations utilizing the vision transformer as the main backbone…more details
Talk | Machine Learning | Intermediate
In this talk, I will discuss the application of machine learning to a broad range of use cases in portfolio and risk management, as well as common pitfalls to look out for when working with financial data…more details
Keynote
On one side, we hear reports pharma and healthcare industry is lagging as opposed to some of the other industries like Retail, Telecom and technology and on other side we hear new innovations, digital therapies, new products being launched in pharma and healthcare – as a data science practitioner, have you ever wondered why is there a contrast? Listen to this talk on some reflections on the various elements on what those could be and any impact on the journey due to the pandemic…more details
Talk | Machine Learning | Beginner-Intermediate
In this talk, I will present some advances that the research community and industry have made in the recent past in developing machine learning techniques to automate software engineering. Along the way, I will relate machine-learning techniques to traditional program analysis techniques. I will discuss representative deep learning methods to analyze and synthesize source code. While much progress is being made, we will see what challenges remain…more details