This paper introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from corpus of programs in domain specific language (DSL). The algorithm builds abstractions directly initial DSL primitives, using syntactic pattern matching intermediate to intelligently prune the search space and guide towards maximally shared structures ...

Unimpaired readers process words incredibly fast and hence it was assumed that top-down processing, such as predicting upcoming words, would be too slow to play an appreciable role in reading. This runs counter the major postulate of the predictive coding framework that our brain continually predicts probable upcoming sensory events. This means, it may generate predictions about the probable up...

To examine the influence of age and reading proficiency on the development of the spoken language network, we tested 6- and 9-years-old children listening to native and foreign sentences in a slow event-related fMRI paradigm. We observed a stable organization of the peri-sylvian areas during this time period with a left dominance in the superior temporal sulcus and inferior frontal region. A ye...

In a paper published in this journal, Norvig (1991) pointed out that memoization of a top-down recognizer program produces a program that behaves similiarly to a chart parser. This is not surprising to anyone familiar with logic-programming approaches to natural language processing (NLP). For example, the Earley deduction proof procedure is essentially a memoizing version of the top-down select...

Hierarchies provide scalability in large networks and are integral to many widely-used protocols and applications. Previous approaches to constructing hierarchies have typically either assumed static hierarchy configuration, or have used bottom-up construction methods. We describe how to construct hierarchies in a top-down fashion, and show that our method is much more efficient than bottom-up ...

We study the deformation fields of feature maps across convolutional network layers under explicit top-down spatial transformations. We propose top-down flow transformer (TFT) by focusing on three transformations: translation, rotation, and scaling. We learn flow transformation generators that are able to account for the hidden layer deformations while maintaining the overall consistency across...

A top-down design flow for suspended MEMS is described, starting with schematic capture of a design topology, followed by behavioral simulation, layout generation, parasitic extraction, and final verification. Support for this flow requires a MEMS hierarchical circuit representation and mapping of process, materials properties, design rules, and parasitic parameters into appropriate technology ...

Attention exhibits characteristic neural signatures in brain regions that process sensory signals. An important area of future research is to understand the nature of top-down signals that facilitate attentional guidance towards behaviorally relevant locations and features. In this review, we discuss recent studies that have made progress towards understanding: (i) the brain structures and circ...