You are viewing content from a past/completed QCon

Presentation: The Fast Track to AI with Javascript and Serverless

Track: Machine Learning: The Latest Innovations

Location: Whittle, 3rd flr.

Duration: 4:10pm - 5:00pm

Day of week: Tuesday

Slides: Download Slides

Share this on:

This presentation is now available to view on InfoQ.com

Watch video with transcript

What You’ll Learn

  1. Hear about some of the JavaScript and AWS solutions to AI and serverless..
  2. Learn patterns for adoption AI services.

Abstract

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 https://www.manning.com/books/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

 

Question: 

What is the work that you are doing today?

Answer: 

A lot of our work involves three threads. We're very active in serverless. And a lot of that is actually looking at legacy world challenged platforms and helping transform them into systems that can run in a serverless way. There's a lot of organizations that have realized that the economic operating model for cloud and particularly around serverless starts to make a lot more sense. So we're helping with a lot of that movement to serverless and also greenfield as well. Increasingly, a lot of that work involves the upgrading of those platforms to have additional machine learning capabilities. That's about augmenting the business process with things like natural language processing and understanding how to extract meaning from text, some image recognition and so on.

Question: 

What are your goals for this talk?

Answer: 

The goals are similar to the book. The talk is based on our book, AI as a Service. And we wrote that to help people get on board with AI services. I think there's a lot of myth and uncertainty around A.I. and Machine Learning. You don't necessarily need to have a team of data scientists and a PhD in Machine Learning because of the commoditization that we're seeing around this technology, engineers can be very effective for the right use cases. And so we're trying to educate and inform developers about how they can get on board with this technology. I suppose the other part of it is that data science is one thing and building machine learning models is another. But that doesn't equate necessarily to a useful product or even a useful internal platform. There's an enormous amount of work around the edges that has to be done in order to operationalize these machine learning solutions. So there's a much wider context around that that we're trying to help educate people on as well.

Question: 

How do you assess the quality of these models?

Answer: 

It's a great question. And of course, it's not just trusting the results. There are all the other subtle issues that come with using people's models, like bias in the results and so on, which is a huge issue at the moment. I suppose the answer is it depends, which I guess is not a very satisfactory answer, but one that is if you're using, say, a more simple point solution such as Textract from Amazon, which allows you to feed in an image and get back all the fields from the image. Say you wanted to extract a passport number, that can be done with an API call and that's much more boolean. It's right or it's wrong. Whereas when you get into things like classification and so on, it can be a little bit grayer. So I suppose the other part of the skill layer is being able to transfer learning with these cloud services. So I don't necessarily need to start from scratch. I can take a service like Comprehend and cross train so I can do my own customization on top of what's already there without needing to start from scratch. The other piece of the picture is the ability to operationalize my own models that I've built. Typically that process would be to use something like TensorFlow initially to do your research and then something like Sage Maker for additional training and then operationalize through those services.

Speaker: Peter Elger

Co-Founder & CEO @fourtheorem

Peter Elger is the co-founder and CEO of fourTheorem, a company providing expertise on next generation cloud architecture, agile development, AI and machine learning. Formerly a physicist working at the JET fusion research project, Peter was previously co-founder and CTO of Stitcher Ads, a social advertising platform and nearForm, a node.js consultancy. Peter holds degrees in physics and computer science and is a co-author of the Node Cookbook as well as several academic papers on software methodology. Peter’s latest book ‘AI as a Service’ is available from Manning Publications.

Find Peter Elger at

Last Year's Tracks