This paper looks at the problem of predicting category labels that mimic how human observers would name objects.
Software Engineering and Programming Languages
Advertisement
When Computers Stand in the Schoolhouse Door
Classification algorithms can lead to biased decisions, so researchers are trying to identify such biases and root them out.
Some of the most perplexing and frustrating experiences that technologists have are with politics and social policy. One that is currently playing out involves encryption, and what (if anything) should be done to regulate it.
Fifty Years of Operating Systems
A recent celebration of 50 years of operating system research yields lessons for all professionals in designing offers for their clients.
Repeatability in Computer Systems Research
To encourage repeatable research, fund repeatability engineering and reward commitments to sharing research artifacts.
Lessons Learned from 30 Years of MINIX
MINIX shows even an operating system can be made to be self-healing.
Technical Perspective: Taming the Name Game
In "Learning to Name Objects," the authors offer a method to determine a basic-level category name for an object in an image.
Computational Learning Techniques Becoming Mainstream
Applying support vector machines to predictive analytics.
Revealing the API Ecosystem and Enterprise Strategy via Visual Analytics
Seeking better understanding of digital transformation.
The Beckman Report on Database Research
Database researchers paint big data as a defining challenge. To make the most of the enormous opportunities at hand will require focusing on five research areas.
The Moral Hazard of Complexity-Theoretic Assumptions
In November 2015, the computing world was abuzz with the news that László Babai proved the Graph-Isomorphism Problem. If Babai’s result holds under scrutiny, it is likely to become one of the most celebrated results in theoretical computer science of the past several decades.
There are trade-offs to be found between a native mode implementation of an application and a browser-based implementation.
The Verification of a Distributed System
A practitioner's guide to increasing confidence in system correctness.
Schema.org: Evolution of Structured Data on the Web
Big data makes common schemas even more necessary.
The Land Sharks Are on the Squawk Box
It turns out riding across America is more than a handy metaphor for building system software.
Phonetic Analytics Technology and Big Data: Real-World Cases
Data from phone interactions can help address customers' complaints, and predict their future purchasing behavior.
YFCC100M: The New Data in Multimedia Research
This publicly available curated dataset of almost 100 million photos and videos is free and legal for all.
Technical Perspective: Catching Lies (and Mistakes) in Offloaded Computation
The system described in "Pinocchio: Nearly Practical Verifiable Computation" refines an important theoretical advance by Gennaro et al. Together, these two works represent a dramatic improvement in speed, generality, and functionality.
Technical Perspective: Program Synthesis Using Stochastic Techniques
The authors of "Stochastic Program Optimization" have developed a stochastic search technique and applied it to program optimization.
Stochastic Program Optimization
By encoding constraints of transformation correctness as terms in a cost function, and using a Markov Chain Monte Carlo sampler to explore the space of all possible code sequences, we are able to generate aggressively optimized versions of a given target code sequence.
Pinocchio: Nearly Practical Verifiable Computation
We introduce Pinocchio, a built system for efficiently verifying general computations while relying only on cryptographic assumptions.
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