You are viewing content from a past/completed QCon -

Track: Machine Learning: The Latest Innovations

Location: Whittle, 3rd flr.

Day of week:

AI and machine learning is more approachable than ever. Discover how ML, deep learning, and other modern approaches are being used in practice.

Track Host: Jay Alammar

VC and Machine Learning Explainer @STVcapital

Through his blog and lessons on Udacity, Jay has helped tens of thousands of people wrap their heads around complex machine learning topics. Jay harnesses a visual, highly-intuitive presentation style to communicate concepts ranging from the most basic intros to data analysis, interactive intros to neural networks, to dissections of state-of-the-art models in Natural Language Processing. Jay is a Partner at STV, a $500m tech venture capital fund.

10:35am - 11:25am

Accuracy as a Failure

When you see a green light, will you cross the street? Or will you still check for cars?

When your machine learning model has demonstrated high accuracy, do you push it to production?

This talk contains cautionary tales of mistakes that might happen when you let your data scientists on a goose chase for accuracy. It may suprise you, but highly accurate models are more damaging than the inaccurate ones. I will also share some work that my team is doing to make sure that chatbots don't fall into this trap.

Vincent Warmerdam, Research Advocate @Rasa

11:50am - 12:40pm

Visual Intro to Machine Learning and Deep Learning

Break into machine learning with this gentle and intuitive journey through central concepts in machine learning -- from the most basic models up to the latest cutting edge deep learning models. This highly visual presentation will give you the mental map of ML prediction models and how to apply them to real-world problems with plenty of examples from existing businesses and products.

Machine learning is rapidly advancing and, in its path, transforming industries and careers.  It enables software to solve certain problems that have vexed other approaches. Yet, even for software engineers, getting started with machine learning can be confusing and overwhelming. But trust me, you've got this. The central concepts are much easier than they might appear at first.  Whether you want to take the first steps into the field or accelerate your understanding of practical models and their applications, this talk is for you.

Jay Alammar, VC and Machine Learning Explainer @STVcapital

1:40pm - 2:30pm

BERT for Sentiment Analysis on Sustainability Reporting

Sentiment analysis is a commonly used technique to assess customer opinion around a product or brand. The data used for these purposes often consists of product reviews, which have (relatively) clear language and are even labeled (e.g. ratings). But when you look at what companies write about their own performance they tend to use more subtle language. According to the Global Reporting Initiative (GRI) guidelines, a sustainability report should be balanced, thus reflecting on both the positive and negative aspects of the companies performance. 

Recent advances in the field of natural language processing (NLP) have brought forth new 'general language understanding' models which obtained great results on a wide range of NLP tasks. One of these models is Google's BERT. In this talk, I will discuss how, in collaboration with our colleagues from the Sustainability department, we created a custom sentiment analysis model capable of detecting these subtleties, and provide them with a metric indicating the balance of a report.

Susanne Groothuis, Sr. Data Scientist in the Advanced Analytics and Big Data team @KPMG

2:55pm - 3:45pm

Machine Learning Open Space

Details to follow.

4:10pm - 5:00pm

The Fast Track to AI with Javascript and Serverless

Most people associate AI and Machine Learning with the Python language. This talk will explore how to get started building AI enabled platforms and services using full stack Javascript and Serverless technologies. With practical examples drawn from real world projects the talk will get you up and running with AI using your existing Node.js chops - no PhD required.

Previously, adopting and applying AI capabilities in a software platform or a typical enterprise technology estate was out of the reach of most developers and required highly skilled experts. Recently, we have seen a rapid growth in the range and capability of cloud native AI services from all the major providers. Armed with a basic understanding of the underlying concepts, developers can now adopt machine learning tools to solve real world business problems and add advanced features to their platforms without needing a multi-year research project. This talk will be based on my book AI as a Service, published by Manning.

Focusing on Node.js and the AWS stack, this talk will cover:
- The range and scope of services available off the shelf today
- How each available service maps to a specific problem area and how to select a services for your specific context
- How these services can be adopted by developers through familiar API interfaces
- Patterns for adoption of AI services that can be used to augment existing systems and platforms with AI capabilities

The talk will then review some full example solutions to specific business problems taken from real world projects that we have recently worked on. All examples are implemented in Javascript and examples include

Problem Context: Triage and route product feedback. In retail and e-commerce it is important that customer feedback from multiple territories be handled quickly by the appropriate department.
Solution: AI Enabled data processing pipeline that performs, language translation, sentiment analysis text classification and message routing
Services used: Translate, Comprehend, Kinesis, SES

Problem context: During a signup process documents need to to be submitted, validated and information extracted e.g. from utility bills or passport
Solution: AI Enabled image recognition and text extraction service
Services used: Textract, Rekognition


Peter Elger, Co-Founder & CEO @fourtheorem

5:25pm - 6:15pm

Speeding Up ML Development with MLFlow

Machine Learning is more approachable than ever before and the number of companies applying Machine Learning to build AI powered applications and products has dramatically increased in recent years.  On this journey of adopting Machine Learning, many companies learn successful Machine Learning projects require good software infrastructure to enable quick experiment iteration, ease of model development and deployment. Some of these large companies have sufficient resources to invest in building the necessary software infrastructure for their needs and the rest of the companies are looking for open source solutions to help them.  

MLflow, an open source platform for the Machine Learning development lifecycle, was created in 2018 to simplify and speed up the development of AI powered applications. It was designed to be extensible and pluggable from day one.  

This session will share the common needs in the Machine Learning development lifecycle and how MLflow can satisfy some of those needs, and it will end with a demo.

Hien Luu, Engineering Manager @LinkedIn focused on Big Data


This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.