JAX London, 7-10 October 2019
The Conference for Java & Software Innovation

Visual Feature Engineering for Machine Learning with JavaScript

Session
Blind Bird Discount Book by June 06 ✓ Save up to £450! ✓ Goodie: Arduino starter kit or Nintendo mini classic Register now

Tensorflow.js brought Machine Learning to JavaScript which enables a wide range of possibilities. Now it is possible to build, train and use ML models directly in the browser. The efficiency of ML models, though, highly depends upon the features they are using. JavaScript allows us to reinforce an ML feature engineering process. It is great for displaying fast-changing data on the web. Additionally, it lets us visualize features as well as the model’s layers and weights in a run-time during model training. Thereby, it gives us useful insights on how features correspond to the result and lets us determine which features are good and which features could be removed. During the session, we will use a model visualization to pick the best features for predicting results of soccer matches played at the FIFA World Cups. We will check the count of matches that teams have won and lost, the count of wins and losses against a particular competitor, goal differences, and stage; we’ll check if it brings more value to play in the home country and how teams perform over time. We will validate our model using match results from the last Mundial in Russia in 2018.

Behind the Tracks

Software Architecture & Design
Software innovation & more
Microservices
Architecture structure & more
Agile & Communication
Methodologies & more
Emerging Technologies
Everything about the latest technologies
DevOps & Continuous Delivery
Delivery Pipelines, Testing & more
Cloud & Modern Infrastructure
Everything about new tools and platforms
Big Data & Machine Learning
Saving, processing & more