StampedeCon AI SummitOctober 17, 2017 - St. Louis, MO
Explore the applications of artificial intelligence for your organization. The world of AI is here, will you be a part of it?
The Growth of AI
The applications of artificial intelligence in the creation of new products and optimizing business operations are growing and boundless. Advanced machine learning techniques, underpinned by the fundamentals of data science, are bringing predictive models to new levels of accuracy and helping drive new products, capabilities, and discoveries.
What do we KNOW?
You have been collecting and reporting on your data, looking backwards in time. Develop predictive models to find patterns and increase your understanding of the factors that drive your business.
How do we LEARN more?
Advanced machine learning capabilities, such as Deep Learning, are advancing our ability to train predictive models. True learning comes as we act on predictive models and learn what data we could add to models to improve their accuracy.
How do we PREDICT?
Predictive analytics allows us to learn from past business data to predict future outcomes and opportunities. Iteratively refine your models based on actual outcomes and new data. Model, prescribe, act, measure, repeat.
(speakers subject to change)
Dr. Stephen Coggeshall
Fraud Analytics Instructor, USC and UCSD
Foundations of Modeling and Machine Learning
This presentation will cover all aspects of modeling, from preparing data, training and evaluating the results. There will be descriptions of the mainline ML methods including, neural nets, SVM, boosting, bagging, trees, forests, and deep learning. common problems of overfitting and dimensionality will be covered with discussion of modeling best practices. Other topics will include field standardization, encoding categorical variables, feature creation and selection. It will be a soup-to-nuts overview of all the necessary procedures for building state-of-the art predictive models.
Bill Shannon , PhD
President and Founder, BioRankings; Professor Emeritus of Biostatistics in Medicine at Washington University School of Medicine in St. Louis
Predicting Outcomes When Your Outcomes are Graphs
In many modern applications data are collected in unusual form. Connectome or brain imaging data are graphs. Wearable devices measuring activity are functions over time. In many cases these objects are collected for each individual or transaction leaving the statistician with the challenge of analyzing populations of data not in classical numeric and categorical formats in big spreadsheets. In this talk I introduce object oriented data analysis with an application we recently developed for regression analysis. This talk will be aimed at the general data scientist and emphasis on the concepts and not mathematical detail. The take home message is how can we use covariates (i.e., meta-data) to predict what the structure of a brain image graph will be.
Data Scientist, IT Analytics Group, Monsanto
Novel Semi-Supervised Probabilistic ML approach to SNP Variant Calling
This talk aims to dive into technical details in machine learning model development, implementation and values it bring to Monsanto breeding pipeline. We genotype over 100 million seeds a year in order to save field resources and product development cycle time. Automation and high throughput production from the lab becomes key to R&D success. In house predictive model development incorporated random forest ensemble based approach with additional features derived from gaussian mixture model. The results show over 95% accuracy with less than 1% false positives/negatives. Model is highly generalizable with over 10 million data points being trained and tested on. The model also offers probabilistic approach to present genotypes in a more meaningful way and help enhanced downstream genomics analyses. The talk targets audience who are in breeding, genetics, molecular biology, and data scientists who are interested in practical applications.
Jeffrey Heaton, PhD
Lead Data Scientist at Reinsurance Group of America (RGA); Adjunct Instructor for the Sever Institute at Washington University; Author of several books about artificial intelligence
Getting Started with Keras and TensorFlow using Python
This technical session provides a hands-on introduction to TensorFlow using Keras in the Python programming language. TensorFlow is Google’s scalable, distributed, GPU-powered compute graph engine that machine learning practitioners used for deep learning. Keras provides a Python-based API that makes it easy to create well-known types of neural networks in TensorFlow. Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to train neural networks of much greater complexity. Deep learning allows a model to learn hierarchies of information in a way that is similar to the function of the human brain.
This presentation will begin by showing how to use TensorFlow with Python 3 on commodity GPU/CPU hardware. The presentation also provides a brief overview of running TensorFlow from Amazon AWS. Neural networks will be demonstrated for the classic data science problems of classification and regression. Additionally, we will discuss how neural networks can make predictions on common data sets and how to interpret those results. While neural networks can adequately perform classic data science tasks, they truly shine in the areas of image recognition and time series processing.
This presentation will also introduce convolution neural networks for computer vision, which allows computers to recognize images. The most state-of- the-art deep learning algorithms are capable of identifying multiple objects within a single image. Some algorithms automatically generate a descriptive caption for an image.
The session will also include long short term memory (LSTM) for time series, which is a very broad machine learning discipline that deals with data where events occur over time. One of the most common areas of time series prediction is financial analysis and prediction over time. However, any series of events can be modeled as time series. Other applications of LSTM include natural language processing (NLP) and speech recognition. This presentation will cover three examples of TensorFlow: regular classification, computer vision and time series.
IT & Data Analytics, The Boeing Company
Machine Learning in Aviation
Technological change is enabling organizations to store, aggregate, and combine data for advanced analytics. Human decision-making will become increasingly supported with automated algorithms, which will help to create new innovative business models, products, and services. In turn, data is evolving from something analyzed by humans, to something consumed. Collaborative innovations are created more and more by end users and customers themselves, rather than being dictated by producers. Therefore, dominant organizations of this century will be the ones that can most efficiently convert information into action.
Data science is the practice of extracting knowledge embedded within data and arranging or correlating this knowledge into actionable insight. The goal of data science is to uncover truths and assemble these into a narrative that can be easily understood by others. Automated algorithms can support human decision-making by continually processing ever-increasing volumes of real-time data, but only draw attention to the specific information that requires it. Underlying data and analytics are often hidden so that attention is focused on important information alone.
However, most algorithms reason by applying knowledge expressed as rules and generate high predictive power for problems that are well understood and problems with comprehensive samplings of data. What happens when you have knowledge with exceptions, incomplete data, error-ridden data, or a changing environment? How do you reason with uncertainty?
Come find out how Boeing is uncovering and approaching these types of problems and generating actionable insights using Machine Learning and Artificial Intelligence.
S. Joshua Swamidass, MD, PhD
Assistant Professor of Laboratory and Genomic Medicine; Faculty Lead, Translational Bioinformatics Institute for Informatics at Washington University in Saint Louis
Demystifying Deep Learning
A collection of new approaches to building and training neural networks, collectively referred to as “deep learning,” are attracting attention across the business and scientific communities. What is deep learning and is this new attention warranted? Our goal is to look past the hype to understand the specific strengths of deep learning with well chosen case studies. Although deep learning requires high expertise to use effectively, it can solve the complex problems that were once out of reach. This presents a new opportunity for academics and companies alike.
Data Scientist, Miner & Kasch
Don’t Start From Scratch: Transfer Learning for Novel Computer Vision Problems
In this session, we’ll discuss approaches for applying convolutional neural networks to novel computer vision problems, even without having millions of images of your own. Pretrained models and generic image data sets from Google, Kaggle, universities, and other places can be leveraged and adapted to solve industry and business specific problems. We’ll discuss the approaches of transfer learning and fine tuning to help anyone get started on using deep learning to get cutting edge results on their computer vision problems.
Senior Research Engineer, Shutterstock
The Search for a New Visual Search, Beyond Language
Words are no longer sufficient in delivering the search results users are looking for, particularly in relation to image search. Text and languages pose many challenges in describing visual details and providing the necessary context for optimal results. Machine Learning technology opens a new world of search innovation that has yet to be applied by businesses.
In this session, Mike Ranzinger of Shutterstock will share a technical presentation detailing his research on composition aware search. He will also demonstrate how the research led to the launch of AI technology allowing users to more precisely find the image they need within Shutterstock’s collection of more than 150 million images. While the company released a number of AI search enabled tools in 2016, this new technology allows users to search for items in an image and specify where they should be located within the image. The research identifies the networks that localize and describe regions of an image as well as the relationships between things. The goal of this research was to improve the future of search using visual data, contextual search functions, and AI. A combination of multiple machine learning technologies led to this breakthrough.
Senior Director of Decision Sciences at Maritz Motivation Solutions
How to Talk About A.I. to Non-analysts!
While artificial intelligence for self-driving cars and virtual assistants gets a lot of the notion of communicating the needs, effectiveness and measurements is complicated when speaking “geek”! The work of an analyst, however, does not just involve conducting data analysis within but communicating, championing and speaking simply when talking to the organization, clients and management.
Experimental Physicist; CEO of Aerial Insights
Geospatial Artificial Intelligence
With the rise of drones, a new onset of high quality aerial imagery is on the rise. Learn how Aerial Insights is leveraging TensorFlow and geospatial technologies to analyze millions of photos and deliver machine vision to the geospatial community.
Vice President, Enterprise Data Analytics and Applications at Post Holdings
Data Science without Data Scientists
This session will focus on how to execute Data Science caliber efforts by creating teams with the attributes of Data Science to deliver meaningful results. As Data Scientists are harder to find and keep, this session should appeal to anyone who is either seeking an alternative approach to executing Data Science delivery or augmenting their current Data Science model with additional options.
Senior Data Scientist, Teradata
AI in the Enterprise: Past, Present & Future
Artificial Intelligence has entered a renaissance thanks to rapid progress in domains as diverse as self-driving cars, intelligent assistants, and game play. Underlying this progress is Deep Learning – driven by significant improvements in Graphic Processing Units and computational models inspired by the human brain that excel at capturing structures hidden in massive complex datasets. These techniques have been pioneered at research universities and digital giants but mainstream enterprises are starting to apply them as open source tools and improved hardware become available. Learn how AI is impacting analytics today and in the future.
Learn how AI is affecting the enterprise including applications like fraud detection, mobile personalization, predicting failures for IoT and text analysis to improve call center interactions. We look at how practical examples of assessing the opportunity for AI, phased adoption, and lessons going from research, to prototype, to scaled production deployment.
Todd Almarayati & Rob Monzyk
Todd is Senior Director, Enterprise Data Architecture, Analytics and Operations and Rob is Sr. Data Scientist – Enterprise Data Science Knowledge Solutions at Express Scripts
Improving Patient Outcomes with Advanced Analytics
Through the combination of the Enterprise Data Science team and the powerful diagnostic platform, MediCUBE, Express Scripts is at the forefront of predictive capabilities in the Healthcare marketplace. Utilizing more than 22 petabytes of data, and through the proprietary scoring system and real-time analysis, Express Scripts identifies fraud, waste and abuse opportunities, including the ability to address the fastest-growing pharma crisis in our country – the opioid epidemic. This session will cover topics related to Express Scripts’ advanced analytics capabilities and the diagnostic platform that incorporates these predictive models to deliver actionable health data insights. The opportunities related to population health risk and ESI’s advanced analytics capabilities and the path to full AI functionality will be discussed.
Join us to learn more about this exciting approach to creating intelligent software and what it means for healthcare.
Data Scientist/Engineer, working primarily in Computer Vision and Machine Learning, Monsanto
Why Should We Trust You? Interpretability of Deep Neural Networks
Despite widespread adoption and success most machine learning models remain black boxes. Many times users and practitioners are asked to implicitly trust the results. However understanding the reasons behind predictions is critical in assessing trust, which is fundamental if one is asked to take action based on such models, or even to compare two similar models. In this talk I will (1.) formulate the notion of interpretability of models, (2.) provide a review of various attempts and research initiatives to solve this very important problem and (3.) demonstrate real industry use-cases and results focussing primarily on Deep Neural Networks.
Igor Zwir, PhD
Assistant Professor, Department of Psychiatry, Washington University School of Medicine, St Louis, MO, Associate Professor, Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain, D&C Intelligent Systems, Founder.
Bringing the Whole Elephant Into View: Can Cognitive Systems Bring Real Solutions to Complex Problems?
Like the story of the six blind men trying to explain the nature of an elephant, current research in cognitive computational systems attempts to identify the nature of an illness, human behavior, or socio-economical phenomenon, from their own perspective.
At present, there is no agreed upon definition for cognitive systems. One large communication corporation defines cognitive systems as a category of technology that uses artificial intelligence, machine learning and reasoning, to enable people and machines to interact more naturally. It also extends and magnifies human expertise and cognition to enable accurate decisions on time. Two of the most famous risk and financial advisory firms agree with that interpretation. A different large corporation, however, considers “cognitive systems” as merely marketing jargon.
If cognitive systems are going to help us solve challenging problems in medicine, economics, or other fields, three aspects must be considered in order to reveal the “true nature of the elephant”.
§ All facets of the problem must be addressed, like the main parts of the elephant had to be touched by the men.
§ These facets must be properly assembled, like the men needed to join hands around the elephant in order to understand what it was.
§ This assembly must be completed within sufficient time to anticipate future decisions. Just like the men needed to know what an elephant is before the next one charges them.
This talk will explain how agnostic (unsupervised, blinded) machine learning findings can be assembled by multiobjective and multimodal optimization research techniques would be utilized to uncover a multifaceted view of the “elephant”, in this case the human being (e.g., genomic variants, personality traits, brain images). It will also give real-world examples of how this knowledge will “extend the human capabilities” by achieving an integrative assessment of the whole person in relation to their risk, which will allow professionals to generate accurate person-centered policies: from personalized diagnoses, business opportunities, or the prevention of outbreaks.
The target audience of this talk includes anyone looking for realistic solutions to complex real life problems.
Chief Data Scientist, Colaberry
From Prototyping to Production : Building an Efficient Pipeline
Organizations have various problems or ideas in domains of AI and have various challenges of taking them to production. This arises from issues that range from as naive as problem identification itself to identifying the right ML algorithms for solving them. Added to this would be the scaling aspects when large datasets are available. In this talk, you will learn about established techniques that begin with sampling data, conducting experiments and presenting results with powerful visualizations. This shall be followed by preparing the algorithms for scaling. This talk will present details about sampling data, Exploratory Analysis and how to select certain approaches while holding off on others for production. We shall also talk about decisions to resolve ambiguity as when to use out-of-box algorithms vs building ML models from scratch from literature. We shall present use cases with Python on our refactored.ai platform. You shall learn about coding practices and organizational aspects that will help Data Scientists, ML Engineers and Data Engineers to collaboratively work to take your ideas to fruition.
Rajiv Shah, PhD
Data Scientist, DataRobot
Automated AI: The Next Frontier in Analytics
This talk will walk through the important building blocks of Automated AI. Rajiv will highlight the current gaps in the analytics organizations, how to close those gaps using automated AI. Some of the issues discussed around automated AI are the accuracy of models, tradeoffs around control when using automation, interpretability of models, and integration with other tools. These issues will be highlighted with examples of automated analytics in different industries. The talk will end with some examples of how automated AI in the hands of data scientists and business analysts is transforming analytic teams and organizations.
Agenda subject to change
|Time||Innovations & Use Cases||Technologies & Methods||Organizational & Operations|
|8:00 – 8:35||
Check-in, Networking and Breakfast
|8:35 – 8:50||
Summit Opening Remarks
|8:50 – 9:35||
S. Joshua Swamidass, MD, PhD
|9:35 – 10:20||
|10:20 – 11:05||
|11:15 – 12:00||
Jeffrey Heaton, PhD
|12:00 – 12:30||
|12:30 – 1:15||
Bringing the Whole Elephant Into View: Can Cognitive Systems Bring Real Solutions to Complex Problems?
Igor Zwir, PhD
Bill Shannon, PhD
|1:25 – 2:10||
Rajiv Shah, PhD
|2:10 – 2:40||
|2:40 – 3:25||
|3:30 – 4:15||
Todd Almarayati & Rob Monzyk
|4:15 – 4:30||
Summit Closing Remarks
|4:30 – 6:00||
Location: Eric P Newman Education Center, Washington University Medical School
320 S Euclid
St. Louis, MO 63110
Metro Parking Garage
This is EPNEC’s primary parking garage.
Located at the corner of Taylor and Children’s Place Avenues.
Daily Rate is $15 – Accepts Cash and Credit Cards
Click Here for Printable Map and Directions
EPNEC is an IACC-certified conference center on the campus of Washington University Medical Center in St. Louis, Missouri
Eric P. Newman Education Center
PARK in Metro Parking Garage at 4560 Children’s Place, St. Louis, MO 63110
Note: Tickets are non-refundable.
Registration Ends on October 16 at 5:00 PM CDT
This is a guest blog post from Teradata, a Premier sponsor of the StampedeCon Artificial Intelligence Conference 2017 in St. Louis on October 17. We’ve got to the stage where we take intelligent machines for granted. We trust them to carry out complex tasks requiring...
This is a guest blog post from Positronic, a Premier sponsor of the StampedeCon Artificial Intelligence Conference 2017 in St. Louis on October 17. Gaining an Edge with a Cogent AI Strategy The Oscar W. Larson Company is a third-generation family-owned business that...
This is a guest blog post from Monsanto, a Community sponsor of the StampedeCon Artificial Intelligence Conference 2017 in St. Louis on October 17. What comes to mind when you think of ‘modern agriculture’? If Monsanto were to answer this question, the words ‘Data...
This is a guest blog post from Colaberry, a Premier sponsor of the StampedeCon Artificial Intelligence Conference 2017 in St. Louis on October 17. Every organization or individual Data Scientists performs a set of tasks in order to run predictions on input datasets....
Implementing Data Science Scoring Models: Important design considerations for real-time and batch access patterns
By Jeff Heaton, Ph.D., Lead Data Scientist, Reinsurance Group of America (RGA) This is a guest post from Jeff Heaton, Ph.D., Lead Data Scientist, Reinsurance Group of America (RGA), a Community sponsor of the StampedeCon Artificial Intelligence Conference 2017 in St....