Learn More
During visual development, projections from retinal ganglion cells (RGCs) to the lateral geniculate nucleus (LGN) in cat are refined to produce ocular dominance layering and precise topographic mapping. Normal development depends upon activity in RGCs, suggesting a key role for activity-dependent synaptic plasticity. Recent experiments on prenatal retina(More)
Learning can increase the rate of evolution of a population of biological organisms (the Baldwin effect). Our simulations show that in a population of artificial neural networks solving a pattern recognition problem, no learning or too much learning leads to slow evolution of the genes whereas an intermediate amount is optimal. Moreover, for a given total(More)
The goal of DARPA’s Machine Reading (MR) program is nothing less than making the world’s natural language corpora available for formal processing. Most text processing research has focused on locating mission-relevant text (information retrieval) and on techniques for enriching text by transforming it to other forms of text (translation, summarization) –(More)
The New Mil lennium Remote Agent (NMRA) wil l be the first on-board AI system to cont ro l an actual spacecraft. The spacecraft domain raises a number of challenges for planning and execution, ranging from extended agency and long-term planning to dynamic recoveries and robust concurrent execution, all in the presence of t ight real-time deadlines, changing(More)
The New Millennium Remote Agent (NMRA) will be the first AI system to control an actual spacecraft. The spacecraft domain places a strong premium on autonomy and requires dynamic recoveries and robust concurrent execution, all in the presence of tight real-time deadlines, changing goals, scarce resource constraints, and a wide variety of possible failures.(More)
model of the domain. Examples of abstractions we use include: hiding details of subsystem interactions controlled by the executive merging a set of detailed component states into abstract states not modeling certain subsystems using conservative resource and timing estimates Some examples are these abstractions are provided in Section 6. These techniques(More)
We designed and trained a connectionist network to generate letterfonns in a new font given just a few exemplars from that font. During learning. our network constructed a distributed internal representation of fonts as well as letters. despite the fact that each training instance exemplified both a font and a letter. It was necessary to have separate but(More)
  • 1