You are viewing content from a past/completed QCon

Track: Solving Software Engineering Problems with Machine Learning

Location: Cyril Magnin III

Day of week: Wednesday

Andrew Ng called AI "the new electricity." Just as electricity changed forever how we solved the engineering problems of the day, artificial intelligence/machine learning stands poised to reshape how we think of modern software engineering.

The Solving Software Engineering Problems with Machine Learning track looks at the interesting use cases and applications of machine learning in what we have thought of traditional software development. We'll uncover real-world experiences of software engineers working with data scientists to build products that leverage machine learning into their platforms. 

Topics we're pursuing include how machine learning is changing our development environments, how we can better make sense of large volumes of notifications/alerts, how the commoditization of machine learning tooling is making it more approachable for the "rest of us," and how machine learning can be used to optimize environments as diverse as the Kubernetes to entire data centers.

Track Host: Wes Reisz

Software/Technical Advisor C4Media & QCon Chair, previous Architect @HPE

Wesley Reisz is the VP of Technology for Section (an Edge PaaS focused on rethinking how the edge is used in DevOps focused application development). Wes also chairs the LFEdge Landscape Working Group and the San Francisco edition of the software conference QCon.

Before joining Section, Wes served as the product owner for all of the English speaking QCon conferences world wide, was a principal architect with HP Enterprise Systems, and, for over 13 years, taught as an adjunct professor for the University of Louisville (Go Cards!).  

At HPE, Wes’ primary roles supported the US Army’s Human Resources (HRC), Recruiting, and Cadet Support Commands based at Fort Knox, Kentucky. Wes was the principal architect for US Army Cadet Command and was known for championing, building, and deploying enterprise portal and identity solutions used by Army Recruiting.

In addition to Wes’ current roles, he hosts a weekly podcast called The InfoQ Podcast. The InfoQ Podcast serves senior early adopter/early majority developers and architects with interviews from some of software’s most important thought leaders. The podcast has been downloaded over 1.5 million times and has weekly listener base of around 14k.

9:00am - 9:40am

Policing the Capital Markets with ML

Cliff Click talks about SCORE, a solution for doing Trade Surveillance using H2O, Machine Learning, and a whole lot of domain expertise and data munging. SCORE pulls in private and public market data and in a few minutes will search it for all sorts of bad behavior and downright illegal activity. It then filters down the billions of rows of data down to human scale with some great visualizations.

Cliff Click, CTO of @CratusTech

10:00am - 10:40am

Document Digitization: Rethinking OCR with Machine Learning

When you think about Document digitisation from a business optimization process perspective, just performing OCR does not truly solve the problem. We at omni:us are building AI systems to support the insurance industry by handling claims. In order to achieve this we are performing various human-esque activities on so many different types of documents like page / document classification, information extraction, semantic understanding to name few. These activities helping in delivering structured information from highly unstructured documents. This structured information is further used in performing activities such as fraud detection, validation and automated claims settlement. 

 

This talk will outline:

  • The problems and approaches we faced when building deep learning networks to solve problems in the information extraction process.
  • Thought process on why and how we chose certain deep learning strategies
  • The requirement for supervised learning
  • Limitations of deep learning networks
  • Planning and executing research activities in short cycles
  • Evolution of team structures to support AI product building
  • Engineering practises required in building AI systems. 

 

Nischal Harohalli Padmanabha, VP of Engineering and Data Science at @Omnius

11:00am - 11:40am

Improving Developer Productivity with Visual Studio Intellisense

In this session, we'll discuss how PM, engineering, and data science came together to build Visual Studio IntelliCode, which delivers context-aware code completion suggestions (IntelliSense). We'll take you through our journey of customer research, model tuning, and an overview of our engineering layout to showcase how you can think about adding AI/ML capabilities to existing tools.

Allison Buchholtz-Au, Program Manager II @Microsoft
Shengyu Fu, Principal Data Scientist Manager @Microsoft

12:00pm - 12:40pm

Ludwig: A Code-Free Deep Learning Toolbox

The talk will introduce Ludwig, a deep learning toolbox that allows to train models and to use them for prediction without the need to write code. It is unique in its ability to help make deep learning easier to understand for non-experts and enable faster model improvement iteration cycles for experienced machine learning developers and researchers alike. By using Ludwig, experts and researchers can simplify the prototyping process and streamline data processing so that they can focus on developing deep learning architectures.

Piero Molino, Senior ML / NLP Research Scientist @UberAILabs

1:40pm - 2:20pm

Lessons Developing Conversational AI Interfaces

This talk will cover building conversational AI using deep learning technologies and lessons learnt in developing conversational interfaces. The first part of the talk will describe recent advances in deep learning that has led to tremendous progress in natural language processing and is making conversational AI a reality. Conversational AI includes intent classification, sequence labeling, understanding dialogs and context, and coming up with responses to users messages. The second part of the talk will address lessons learned developing conversational interfaces. A conversational interface needs to be personable in addressing, adaptive in understanding, and available with many different supported tasks. Overall, key take aways from the talk will be better understanding of (1) deep learning techniques for natural language processing and (2) interaction patterns for building a good conversational interface.

Mitul Tiwari, Cofounder and CTO of @PassageAI

2:40pm - 3:20pm

Panel: First Steps with Machine Learning

Throughout the day, we'll have speakers cover how they've adopted applied machine learning to software engineering. The day wraps with a discussion from the speakers on taking an applied, pragmatic approach to adding ML to you systems and how they solved challenges. Eager to deploy ML and have questions? This is a forum to discuss, learn, and help crystalize that roadmap. Join Cliff Click, Soups Ranjan, and the track speakers as they discuss first principles adding ML to your systems.

Nischal Harohalli Padmanabha, VP of Engineering and Data Science at @Omnius
Shengyu Fu, Principal Data Scientist Manager @Microsoft
Soups Ranjan, Financial Crime Risk @RevolutApp
Cliff Click, CTO of @CratusTech

2019 Tracks