AG2PI Workshop #17 - Friday December 9, 2022


Train Your Network: Simplifying Computer Vision Application Development

Friday December 9, 2022 @ 11:00 AM - 1:00 PM (US Central Time)
Download Flyer
Friday December 9, 2022
11:00 AM - 1:00 PM
(US Central Time)

Purpose

Demonstrate a new image classification program, Train Your Network, designed for use by anyone, including the most novice users of AI.

Registration

(Virtual Zoom Meeting)

Register for the virtual event by clicking the link below. Upon registration, you will receive a confirmation email with information about joining the meeting

Workshop Registration

Workshop Resources

Click the buttons below to access resources and/or watch recording of this workshop

Watch Workshop Recording

In this workshop, we will discuss the background and motivations for developing Train Your Network, a software aimed at facilitating the creation of customized computer vision tools for non-expert users. We will demonstrate how to use the developed tool to train customized deep learning algorithms to perform image classification, a common computer vision task, on datasets provided by the user. An easy-to-use user interface allows users with no previous programming experience to train their own image classification neural networks and use such networks to perform predictions on newly chosen images. Our goal is to create more accessible user interfaces so that coding abilities are no longer a barrier for developing computer vision applications.

** This work was supported with an AG2PI seed grant **

View AG2PI Funded Seed Grant

About Presenters

Dr. Rafael Ferreira

Rafael Ferreira is an Electrical and Computer Engineer & Ph.D. candidate in the Animal & Dairy Sciences department at University of Wisconsin-Madison, in Dr. Dorea's lab. He is currently interested in developing computer vision systems to improve dairy farm management and phenotyping.


Dr. Tiago Bresolin

Tiago Bresolin is an Assistant Professor in the Department of Animal Sciences at University of Illinois Urbana-Champaign. His research explores statistical & computational biology methods to analyze large phenotype and genomic datasets, leveraging the power of machine learning and camera systems to generate novel and difficult-to-measure phenotypes, and integrating multi-omics data using statistical and machine learning techniques.


Dr. Joao Dorea

Joao Dorea is an Assistant Professor in the Department of Animal and Dairy Sciences at the University of Wisconsin-Madison. His research focuses on precision agriculture and data analytics to improve farm management decisions using phenotypng methods such as computer vision systems, wearable sensors, and infrared spectroscopy to monitor animal nutrition, health, and welfare.