Communications of the ACM
Why the Simplex Method, at Age 75, is Still the Go-To Algorithm
Daniel A. Spielman and colleague Shang-hua Teng solved the mystery of the Simplex Method using a technique called smoothed analysis… From ACM NewsAn edited collection of advanced computing news from Communications of the ACM, ACM TechNews, other ACM resources, and news sites around the Web.
From ACM TechNews
ML Speeds Up Vehicle Routing
A new machine learning approach could speed up vehicle routing algorithms, which tend to slow down when applied to large urban datasets.
From ACM TechNews
ML Flags Remedies That Might Do More Harm Than Good
Scientists designed a machine learning model to identify medical treatments that could pose greater potential danger than alternatives.
From ACM TechNews
Tiny ML Design Alleviates Bottleneck in Memory Usage on IoT Devices
Researchers come up with a machine learning method to reduce the amount of memory required for Internet of Things devices.
From ACM TechNews
Taking Some Guesswork Out of Drug Discovery
The deep learning GeoMol model can rapidly predict the three-dimensional shapes of drug-like molecules, which could expedite drug discovery.
From ACM TechNews
Timber or Steel? Study Helps Builders Reduce Carbon Footprint of Truss Structures
Architects and engineers could design truss structures minimizing embodied carbon by using a new set of computational tools.
From ACM TechNews
Making ML More Useful to High-Stakes Decision Makers
An international research team developed a visual analytics tool to address challenges faced by child welfare specialists using machine learning models to screen...
From ACM TechNews
Accelerating the Discovery of Materials for 3D Printing
Researchers have developed a less costly, less wasteful machine learning system for identifying three-dimensionally-printable materials.
From ACM TechNews
These Neural Networks Know What They're Doing
Researchers have shown that a specific neural network can learn the cause-and-effect structure of a navigation task it is taught.
From ACM TechNews
Tool for Predicting Pedestrian Flow Expands Its Reach
Massachusetts Institute of Technology researchers have developed and applied a predictive model of pedestrian traffic to Melbourne, Australia.
From ACM TechNews
Deep Learning Helps Predict Drug Combinations to Fight COVID-19
A research team used deep learning to identify drug combinations that can fight COVID-19.
From ACM TechNews
Study: Crowds Can Wise Up to Fake News
Scientists suggest crowdsourced assessments from groups of normal readers can virtually match those of professional fact-checkers in vetting news stories.
From ACM TechNews
Machine Learning Discovers Sequences to Boost Drug Delivery
Researchers have developed an approach that uses experimental chemistry and artificial intelligence to facilitate delivery of a drug to treat Duchenne muscular...
From ACM TechNews
Creating 'Digital Twins' at Scale
Researchers have designed a model for generating digital twins—precise computer simulations—at scale.
From ACM TechNews
AI System Could Help Counter the Spread of Disinformation
The Reconnaissance of Influence Operations program was developed to identify disinformation narratives and the individuals spreading them via social media.
From ACM TechNews
Slender Robotic Finger Senses Buried Items
Researchers have developed a slender robot finger with tactile sensing capabilities that can help locate and identify buried objects.
From ACM TechNews
System Cleans Messy Data Tables Automatically
A system developed by researchers at the Massachusetts Institute of Technology automatically cleans "dirty data."
From ACM TechNews
One-Stop Machine Learning Platform Turns Healthcare Data Into Insights
Software developed by researchers at the Massachusetts Institute of Technology uses machine learning to transform healthcare data into insights that can inform...
From ACM TechNews
Robot Senses Hidden Objects
A new robot can locate and grasp hidden objects using radio waves in combination with traditional computer vision.
From ACM TechNews
System Detects Errors When Medication is Self-Administered
Massachusetts Institute of Technology researchers have developed a system to detect and reduce errors when patients administer their own medication.
From ACM TechNews