9:00am–12:30pm Tuesday, April 16, 2019
Secondary topics:
Deep Learning and Machine Learning tools,
Models and Methods
Gunnar Carlsson explains how to use topological data analysis to describe the functioning and learning of a neural network in a compact and understandable way—resulting in material speedups in performance (training time and accuracy) and enabling data-type customization of neural network architectures to further boost performance and widen the applicability of the method to all datasets.
Read more.
11:05am–11:45am Wednesday, April 17, 2019
Secondary topics:
Computer Vision,
Ethics, Privacy, and Security,
Models and Methods
Siwei Lyu reviews the evolution of techniques behind the generation of fake media and discusses several projects in digital media forensics for the detection of fake media, with a special focus on recent work on detecting AI-generated fake videos (DeepFakes).
Read more.
11:05am–11:45am Wednesday, April 17, 2019
Location: Grand Ballroom West
Secondary topics:
Models and Methods
Much of today's data is noisy, incomplete, heterogeneous in nature, and interlinked in a myriad of complex ways. Lise Getoor discusses AI methods that are able to exploit both the inherent uncertainty and the innate structure in a domain. Along the way, Lise explores the benefit of utilizing structure—and the inherent risk of ignoring structure.
Read more.
1:00pm–1:40pm Wednesday, April 17, 2019
Secondary topics:
Data and Data Networks,
Models and Methods,
Reinforcement Learning
Join Danny Lange to learn how to create artificially intelligent agents that act in the physical world (through sense perception and some mechanism to take physical actions, such as driving a car). You'll discover how observing emergent behaviors of multiple AI agents in a simulated virtual environment can lead to the most optimal designs and real-world practices.
Read more.
1:50pm–2:30pm Wednesday, April 17, 2019
Location: Grand Ballroom West
Secondary topics:
Models and Methods,
Platforms and infrastructure
The AI industry needs new software architectures for distributed systems to solve critical problems. Vinay Rao and Santi Adavani explain why software architectures will lead the next generation of machine learning approaches and how RocketML has built logistic regression models on the KDD12 dataset with ~150 million samples on an eight-Intel Xeon-node cluster in under a minute.
Read more.
4:05pm–4:45pm Wednesday, April 17, 2019
Location: Grand Ballroom West
Haizi Yu (University of Illinois at Urbana-Champaign)
Can an AI learn the laws of music theory from sheet music in the same human-interpretable form as a music theory textbook? How little prior knowledge is needed to do so? Haizi Yu considers questions like these as he walks you through developing a general framework for automatic concept learning.
Read more.
4:55pm–5:35pm Wednesday, April 17, 2019
Location: Grand Ballroom West
Secondary topics:
Ethics, Privacy, and Security,
Models and Methods
In recent years, we've seen tremendous improvements in artificial intelligence, due to the advances of neural-based models. However, the more popular these algorithms and techniques get, the more serious the consequences of data and user privacy. Yishay Carmiel reviews these issues and explains how they impact the future of deep learning development.
Read more.
1:00pm–1:40pm Thursday, April 18, 2019
Location: Grand Ballroom West
Secondary topics:
AI case studies,
Automation in machine learning and AI,
Deep Learning and Machine Learning tools
Automated machine learning (AutoML) enables both data scientists and domain experts (with limited machine learning training) to be productive and efficient. AutoML is a fundamental shift in how organizations approach machine learning. Francesca Lazzeri and Wee Hyong Tok demonstrate how to use AutoML to automate the selection of machine learning models and automate tuning of hyperparameters.
Read more.
1:00pm–1:40pm Thursday, April 18, 2019
Secondary topics:
Models and Methods,
Text, Language, and Speech
Ming-Wei Chang offers an overview of a new language representation model called BERT (Bidirectional Encoder Representations from Transformers). Unlike recent language representation models, BERT is designed to pretrain deep bidirectional representations by jointly conditioning on both left and right context in all layers.
Read more.
1:50pm–2:30pm Thursday, April 18, 2019
Location: Grand Ballroom West
Secondary topics:
Financial Services,
Models and Methods,
Temporal data and time-series
Arun Kejariwal and Ira Cohen share a novel two-step approach for building more reliable prediction models by integrating anomalies in them. They then walk you through marrying correlation analysis with anomaly detection, discuss how the topics are intertwined, and detail the challenges you may encounter based on production data.
Read more.
2:40pm–3:20pm Thursday, April 18, 2019
Location: Grand Ballroom West
Secondary topics:
Computer Vision,
Models and Methods,
Text, Language, and Speech
Anoop Katti explores the shortcomings of the existing techniques for understanding 2D documents and offers an overview of the Character Grid (Chargrid), a new processing pipeline pioneered by data scientists at SAP.
Read more.
4:05pm–4:45pm Thursday, April 18, 2019
Location: Grand Ballroom West
Secondary topics:
Media, Marketing, Advertising,
Models and Methods,
Retail and e-commerce
Recommender systems support decision making with personalized suggestions and have proven useful in ecommerce, entertainment, and social networks. Sparse data and linear models are a burden, but the application of deep learning sets new boundaries and offers remarkable results. Join Marcel Kurovski to explore a use case for vehicle recommendations at Germany's biggest online vehicle market.
Read more.
4:55pm–5:35pm Thursday, April 18, 2019
Location: Grand Ballroom West
Secondary topics:
AI in the Enterprise,
Models and Methods
AI planning offers an opportunity to drive reasoning about action trajectories to help build automation. Maja Vukovic demos an application of AI planning for the migration of legacy infrastructure to the cloud, based on real-world examples and data, and discusses challenges in adopting AI planning solutions in the enterprise.
Read more.
4:55pm–5:35pm Thursday, April 18, 2019
Location: Trianon Ballroom
Secondary topics:
Media, Marketing, Advertising,
Models and Methods,
Reinforcement Learning
Matthew Reyes casts consumer decision making within the framework of random utility and outlines a simplified scenario of optimizing preference on a social network to illustrate the steps in a company’s allocation decision, from learning parameters from data to evaluating the consequences of different marketing allocations.
Read more.