Computer Sciences
A key limitation of existing artificial intelligence (AI) systems is that they are unable to tackle tasks for which they have not been trained. In fact, even when they are retrained, the majority these systems are prone to ...
Mar 12, 2019 feature
0
206
Computer Sciences
Researchers at Clova AI Research, NAVER and LINE, have recently proposed a new framework called AQM+ that allows dialog systems to generate context-relevant questions and answers. Their model, outlined in a paper pre-published ...
Mar 08, 2019 feature
0
148
Robotics
A novel system developed at MIT uses RFID tags to help robots home in on moving objects with unprecedented speed and accuracy. The system could enable greater collaboration and precision by robots working on packaging and ...
Feb 19, 2019
0
24
Robotics
It took just over 10 years, but real science has finally caught up to the science fiction of Iron Man's transforming exoskeleton suit.
Feb 13, 2019
0
1928
Robotics
Researchers at the University of Utah have recently developed a probabilistic grasp planner that can explicitly model grasp types to plan high-quality precision and power grasps in real time. Their supervised learning approach, ...
Jan 28, 2019 feature
0
90
Computer Sciences
Researchers from the Embedded Systems and Robotics group at TCS Research & Innovation have recently developed a two-view depth network to infer depth and ego-motion from consecutive monocular sequences. Their approach, presented ...
Jan 17, 2019 feature
1
169
Computer Sciences
Organizations looking to benefit from the artificial intelligence (AI) revolution should be cautious about putting all their eggs in one basket, a study from the University of Waterloo has found.
Jan 17, 2019
2
47
Computer Sciences
Researchers at the University of Wisconsin-Madison and Amherst College have recently introduced a new form of steganography in the domain of machine learning called "training set camouflage." Their framework, outlined in ...
Jan 04, 2019 feature
0
161
Computer Sciences
Researchers at the Australian National University (ANU) have recently carried out a study exploring extractive summarization in comparative settings. The term 'extractive summarization' defines the task of selecting a few ...
Dec 17, 2018 feature
0
35
Robotics
Imitation learning is a branch of machine learning that trains machines to mimic human behavior while completing particular tasks. These techniques show great promise in the field of robotics, as they tackle some of the shortcomings ...
Nov 21, 2018 feature
0
68
Robotics
Researchers at MIT's Computer Science and Artificial Intelligence Laboratory have recently developed a chance-constrained motion planning system that can be applied to high degree-of-freedom (DOF) robots under motion uncertainty ...
Nov 20, 2018 feature
1
33
Robotics
Researchers at the Royal Institute of Technology (KTH) and National Oceanography Centre have recently used behavior trees (BTs) to design modular, versatile, and robust control architectures for critical missions. Their study, ...
Nov 12, 2018 feature
0
75
Machine Learning & AI
Researchers at Carnegie Mellon University have recently developed a new model that enables fast and accurate object detection in high-resolution 4K and 8K video footage using GPUs. Their attention pipeline method carries ...
Nov 07, 2018 feature
0
120
Robotics
General-purpose robots have plenty of limitations. They can be expensive and cumbersome. They often accomplish only a single type of task.
Oct 31, 2018
0
98
Computer Sciences
Behind most of today's artificial intelligence technologies, from self-driving cars to facial recognition and virtual assistants, lie artificial neural networks. Though based loosely on the way neurons communicate in the ...
Oct 17, 2018
1
777
