Artificial intelligence and its practical toolset of machine learning have enormous potential for medical applications. A technical team working on such datasets may seek open source tools and quickly face a myriad of options. I present two recent projects and extract learnings for hardware and software tools to build and deploy models. The two projects include fully unsupervised clustering for high-content microscopy images and retinal imaging for retinopathy screening. Respectively, they investigate novel deep learning approaches for semantic segmentation and application-specific network architectures. Software tools surveyed and used in our projects include NVIDIA DIGITS, BVLC Caffe, NYU Torch7, and Google Tensorflow frameworks.
The lessons gleaned from these case studies help scope the dataset requirements, engineering economy, and application feasibility. Emerging from the case studies are a series of recommendations that may constitute best practices for industrial deep learning applied to disparate data sources and applications.
Speaker: Leo Tam – Software Engineer, NVIDIA
Leo Tam serves as Solutions Architect and Deep Learning Community Manager, part of the NALA-based, World Wide Field Organization (WWFO). He focusses on curating open source tools, advising and architecting solutions for enterprise applications, and contributing to the Deep Learning Institute, which his team established. Leo Tam brings to NVIDIA 10 years of R&D experience, previously as a scientist at Stanford’s School of Medicine. He is a top performer in algorithm’s competitions including placing in the top 3% of a world-wide competition sponsored by the California Healthcare Foundation and second place in a commodities trading competition. Leo holds multiple patents for MRI machine learning and encoding methods developed at the Yale University School of Medicine. Leo earned his BSc in Mathematics – Physics from Brown University and PhD from Yale University.
When: Thursday 7th September 2018, 3 pm to 4.30 pm
Location : Curate Space, Level 6, 306 Little Collins Street
A Recording of the session will be made available on demand in the coming days.
Curate Space is the Victorian Government’s Digital Innovation Festival Hub.
We are proud to be partnering with the Victorian Government to deliver a ten day program of events, for audiences in the venue and online via the live stream. We are also the home for the festival team, working from our Festivals and Events Industry Coworking Space.
The 2018 DIF Hub will host sessions over 10 days of the festival from Monday 28 August to Friday 7 September 10.00am – 7.30pm at Curate Space in the heart of the Melbourne CBD.
Curate Space is an event partner with the Victorian Government