Advances in machine learning are announced every day, but efforts to fundamentally rethink the core algorithms of AI are rare.
Text was considered relatively safe from adversarial attacks, because, whereas a malicious agent can make minute adjustments to an image or waveform of sound, it can’t alter a word by, say, 1%. But Prof. Alex Dimakis of Texas ECE and his collaborators have investigated a potential threat to text-comprehension AIs.
The Engineering Education and Research Center at The University of Texas was abuzz with over 200 participants gathered for Texas Wireless Summit (TWS) on November 6. This year’s theme was “AI and the Mobile Device.”
Held annually by WNCG, TWS brings together leading figures in industry, academia, and government to discuss the latest developments in information systems technology. “AI and the Mobile Device” marked the 16th summit hosted by the group.
We present two examples of using machine learning to improve end-user quality of experience (QoE) in cellular networks operating today. In particular, we demonstrate how to automate the clearing of operational faults in outdoor networks and compensation of signal impairments in indoor networks for voice-over-LTE (VoLTE) applications. Our proposed methods are compatible with 3GPP LTE Release 8 and higher.
Texas ECE Professors Andreas Gerstlauer and Lizy K. John together with collaborators at the University of California, Riverside have been awarded a $1M grant by the National Science Foundation (NSF) to study application of machine learning techniques for performance and power prediction in early design stages of future computer systems.
The project is described below:
Texas ECE alumna Jette Henderson, who completed her PhD in August, received the Best Student Paper award for the paper "PIVETed-Granite: Computational Phenotypes through Constrained Tensor Factorization" at the KDD MLMH Workshop on Machine Learning for Healthcare in London in August. Jette worked under the supervision of Texas ECE professor Joydeep Ghosh. The paper uses a special kind of tensor factorization that is guided by supporting evidence from PubMed, a huge repository of medical literature, to extract meaningful insights from electronic health records.
Picture your typical hospital scene: Patients being admitted at the front desk, doctors performing consultations, nurses administering medicine … and robots wandering the hallways toward the supply closet?
Robots in the storeroom may not be the norm quite yet, but it’s happening in Austin thanks to WNCG professor Andrea Thomaz and her company, Diligent Robotics.
Prof. Robert Heath delivered a keynote speech at IEEE Communication Society’s 2018 International Conference on Communications (IEEE ICC).
Prof. Edison Thomaz of Texas ECE has received a Google Faculty Research Award for his proposed research work on "Identifying Acoustic Biomarkers of Mental Health and Well-Being in Voice-Based Interactions with Conversational Assistants in the Home".