Author: SRI International
-
MULTI-SCALE REGULARIZED DEEP NETWORK FOR RETINAL VESSEL SEGMENTATION
We propose a novel domain enriched deep network that consists of two components: 1) a representation network which learns geometric (specifically curvilinear) features that are tailored to retinal images, followed by 2) a task network that utilizes the features obtained from the representation layer to perform pixel-level segmentation.
-

Tech history: the story behind Stanford’s satellite dish hiking trail in Palo Alto
The scoop on the past and present of the famous radio telescope that is still active today
-
Fibridge: Embedded fiber-optic sensing for low-cost, high resolution monitoring in bridges and IoT-connected systems
This talk will give an overview of the project, enabling technologies, and summarize key results on vehicle load and structural response features detectable, bridge state estimation algorithm development, low-cost optical readout development, and validation test results.
-

Making learning relevant: infusing real-world experiences into the classroom for lasting college, career and life success
SRI International’s nine-year evaluation of the initiative unlocked promising evidence on improved student outcomes, including increased credit accumulation and graduation rates.
-

Early education that leads to school readiness: proven lessons for creating a strong start with high-quality preschool environments
Preschool is the building block to lasting education success, but high-need communities often lack high-quality preschool experiences that promote school readiness.
-

Building on open educational resources: helping students complete a degree without purchasing a single textbook
Investigating whether replacing traditional materials with freely available and openly licensed resources can increase college affordability and academic success.
-

Automating chemical drug discovery and synthesis
SRI International’s continuous flow SynFini™ Suite produced multiple nucleoside antivirals in a single day. The SynFini Suite consists of three integrated components – SynRoute ™, SynJet™ and AutoSyn™ – that automatically design synthetic routes for molecules of interest, conduct subsequent reaction screening and optimization, and then produce the selected molecules on scales from micrograms to…
-

In AI we trust? How might we design intelligent systems that inspire trust?
How might we design intelligent systems that inspire trust?
-
Identifying Transfer Student Subgroups by Academic and Social Adjustment: A Latent Class Analysis
This study used a latent class analysis to examine whether meaningful subgroups of transfer students emerged based on their response patterns to measures of academic and social adjustment.


