A new DARPA program is teaching cameras visual intelligence — how to spot and understand human behavior.
Artificial Intelligence and Machine Learning
Advertisement
Improving Brain-Computer Interfaces
Researchers are demonstrating advances in restorative BCI systems that are giving paralyzed individuals more effective ways to communicate, move, and interact with their environment.
A new paradigm is needed to cope with the application, technology, and discipline challenges to our computing profession in the coming decades.
Technical Perspective: A Better Way to Learn Features
A typical machine learning program uses weighted combinations of features to discriminate between classes or to predict real-valued outcomes. The art of machine learning is in constructing the features, and a radically new method of creating features constitutes a major advance.
Technical Perspective: Power Efficiency as the #1 Design Constraint
Moore's Law, and associated observations by Bob Dennard, describe key technical foundations of the semiconductor industry. Taking a step back from these insightful assertions, we can see an even bigger picture emerge related to energy usage and power consumption.
Technical Perspective: Visual Reconstruction
Nearly 460,000 Flickr pictures were used to create detailed three-dimensional geometry and colors of famous landmarks and monuments in Rome, Venice, and Dubrovnik. To computer vision researchers, these visual reconstructions are a dream come true.
Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks (DBNs); however, scaling such models to full-sized, high-dimensional images remains a difficult problem.
Understanding Sources of Ineffciency in General-Purpose Chips
To better understand what improvement in processor efficiency is possible, we quantify the performance and energy overheads of a 720p HD H.264 encoder running on a CMP system. We explore methods to eliminate these overheads by transforming the CPU into a specialized system for H.264 encoding.
We present a system that can reconstruct 3D geometry from large, unorganized collections of photographs. Our experimental results demonstrate that it is possible to reconstruct city-scale image collections with more than a hundred thousand images in less than a day.
Protecting Users of the Cyber Commons
Establish a global cyber "neighborhood watch" enabling users to take defensive action to protect their operations.
Realizing the Future of Wireless Data Communications
Technologies are available to unlock radio spectrum as consumers need it.
A Breakthrough in Algorithm Design
Computer scientists at Carnegie Mellon University have devised an algorithm that might be able to solve a certain class of linear systems much more quickly than today's fastest solvers.
In Praise of ‘Wilkes, Wheeler, and Gill’
Sixty years ago, Maurice Wilkes, David Wheeler, and Stanley Gill produced the first textbook on programming: The Preparation of Programs for an Electronic Digital Computer. It was a publication that spearheaded the software revolution.
Quantitative Analysis of Real-Time Systems Using Priced Timed Automata
Timed automata and their extensions allow for analysis of a wide range of performance and optimization problems.
A New Benchmark For Artificial Intelligence
Computers are unable to defeat the world's best Go players, but that may change with the application of a new strategy that promises to revolutionize artificial intelligence.
Supercomputing’s Exaflop Target
The twin challenges of parallelism and energy consumption are enlivening supercomputers' progress.
The Holy Grail of language translation is to develop a machine-based system that can handle the task transparently and accurately.
The Robustness Principle Reconsidered
In 1981, Jon Postel formulated the Robustness Principle. Although described for implementations of TCP, it was quickly accepted as a good proposition for implementing network protocols in general. It's simple, easy to understand, and intuitively obvious. But is it correct?
Heterogeneous systems allow us to target our programming to the appropriate environment.
Unite neuroscience, supercomputing, and nanotechnology to discover, demonstrate, and deliver the brain's core algorithms.
Does IBM's Watson represent a distinct breakthrough in machine learning and natural language processing or is the 2,880-core wunderkind merely a solid feat of engineering?
Self-driving cars are inching closer to the assembly line, thanks to promising new projects from Google and the European Union.
Searching For Jim Gray: A Technical Overview
The volunteer search for Jim Gray, lost at sea in 2007, highlights the challenges of computer-aided emergency response.
A Decade of Software Model Checking with SLAM
SLAM is a program-analysis engine used to check if clients of an API follow the API's stateful usage rules.
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get InvolvedCommunications of the ACM (CACM) is now a fully Open Access publication.
By opening CACM to the world, we hope to increase engagement among the broader computer science community and encourage non-members to discover the rich resources ACM has to offer.
Learn More