The lack of effective data integration and knowledge representation in patient monitoring limits its utility to clinicians. Intelligent alarm algorithms that use artificial intelligence techniques have the potential to reduce false alarm rates and to improve data integration and knowledge…

If we are to understand human-level intelligence, we need to understand how meanings can be learned without explicit instruction. I take a step toward that understanding by focusing on the symbol-grounding problem, showing how symbols can emerge from a system…

Speech synthesis is an automatic encoding process carried out by machine through which symbols conveying linguistic information are converted into an acoustic waveform. In the past decade or so, a recent trend toward a non-parametric, corpus-based approach has focused on…

Understanding the biological signals encoded in a genome is a key challenge of computational biology. These signals are encoded in the four-nucleotide alphabet of DNA and are responsible for all molecular processes in the cell. In particular, the genome contains…

If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have…

Satellite and wireless networks operate over time varying channels that depend on attenuation conditions, power allocation decisions, and inter-channel interference. In order to reliably integrate these systems into a high speed data network and meet the increasing demand for high…

The collaboration of researchers in different fields, institutions, and nations continues to be important as new ideas and solutions result from the combination of different knowledge and experiences. The Cambridge MIT Institute (CMI) Online Project Assessment System(OPAS) aims to collect…

Heavily used in the manufacture of integrated circuits, chemical-mechanical polishing (CMP) is becoming an enabling technology for microelectromechanical systems (MEMS). To reliably use CMP in the manufacturing process, designers must be able to accurately predict the CMP process and control…

Intelligent autonomous agents working cooperatively accomplish tasks more efficiently than single agents, as well as tasks that were infeasible for the single agent. For example, a single agent transporting a ton of blocks will need to take multiple trips, possibly…

To take further steps along the path toward true artificial intelligence, systems must be built that are capable of learning about the world around them through observation and explanation. These systems should be flexible and robust in the style of…