Skip to content

Details

We are delighted to welcome you to our in person event in March 2024!

Schedule

18:00--18:45h: Refreshments (Food served on first come first served basis)

18:45--18:50h: Welcome

18:50--19:20h: Steve Boyle @ JetSoft

19:20--19:30h: Intermission

19:30--20:00h: Rithwik Rajendran @ LS Eleven, ASDA

Steve Boyle, Small Data for Neural Networks

Convolutional neural networks are well established as a tool for image classification and machine vision tasks, with many applications and impressive results. In general, such techniques require a large amount of training data, ideally thousands of images – but what can be done when this is not available?

JetSoft have successfully applied neural network models for clients in the aerospace manufacturing sector, identifying specific types of material defects to assist in quality control and process improvement. Access to labelled training data for these implementations was extremely limited, so various techniques were explored to compensate for this. The insight provided by these tools has helped to track down the root cause of various defects, reducing scrappage and resulting in less waste and lower costs.

This talk will discuss pragmatic approaches to training neural networks on small datasets, including generalization parameters, pre-processing of training data, and generating simulated data.

Steve Boyle bio

JetSoft provide data solutions to industry, specialising in software for Non-Destructive Testing and proactive approaches to data analysis and process improvement.

After a PhD in Physics, and several years as a full stack .NET developer, Steve joined JetSoft to lead the development of applications for data management, visualisation of scan data, and automated classification.

Rithwik Rajendran, Navigating an end-to-end Machine Learning Workflow on Databricks

In this presentation, Rithwik Rajendran will lead an exploration into the journey of transforming a simple machine learning model into a fully-fledged data product, employing Databricks as the foundational platform. Rithwik will illuminate critical considerations, including data preparation, feature engineering, model selection, and evaluation, demonstrating how each step contributes to the overall success of the project.

Whether you're a data scientist, engineer, or decision-maker, this session provides valuable insights to elevate your approach to deploying machine learning models as impactful data products.

Rithwik Rajendran bio

Rithwik is a Data Scientist at LS Eleven, part of the ASDA Group where he focuses on building models & data products. Rithwik worked as a Data Scientist at Wipro Limited before completing his MSc in Data Science from the University of Bristol. Rithwik’s worked in the public football analytics community & has had a tutorial published on the Matplotlib official blog.

News and Announcements

Have a news item or announcement you'd like to make about upcoming data events or job opportunities in Leeds? Comment below or contact us directly and we'll do our best to circulate this information at the end of the session. Please contact the organisers if you would like to volunteer as a speaker for future events.

Related topics

Events in Leeds, GB
Machine Learning
Data Analytics
Data Mining
Data Science

You may also like