Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networks to perform tasks in which input/output dependencies span long intervals. Starting from a mathematical analysis of the problem, we consider and compare alternative algorithms and architectures on tasks for which the ...

Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networks to perform tasks in which input/output dependencies span long intervals. Starting from a mathematical analysis of the problem, we consider and compare alternative algorithms and architectures on tasks for which the ...

Providing timely results in the face of rapid growth in data volumes has become important for analytical frameworks. For this reason, frameworks increasingly operate on only a subset of the input data. A key property of such sampling is that combinatorially many subsets of the input are present. We present KMN, a system that leverages these choices to perform data-aware scheduling, i.e., minimi...

A simple Neural Network model is presented for end-to-end visual learning of arithmetic operations from pictures of numbers. The input consists of two pictures, each showing a 7-digit number. The output, also a picture, displays the number showing the result of an arithmetic operation (e.g., addition or subtraction) on the two input numbers. The concepts of a number, or of an operator, are not ...

Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networks to perform tasks in which input/output dependencies span long intervals. Starting from a mathematical analysis of the problem, we consider and compare alternative algorithms and architectures on tasks for which the ...

A touchpad is a common input device for notebook computers. However, pointing performance is poor in comparison with a mouse. This research is motivated by the need to improve the touchpad as an input device -to bring it closer to a mouse in pointing performance. To learn how users operate the touchpad during pointing tasks, we measured the force applied to the touchpad. We also measured the fo...

Background: Within cognitive neuropsychological models, conduction aphasia has been conceptualized as a phonological buffer deficit. It may affect the output buffer, the input buffer, or both. The phonological output buffer is a short-term storage, responsible for the short-term maintenance of phonological units until their articulation, as well as for phonological and morphological composition...

The present study investigated the effects of three types of input-based approaches, deductive instruction, inductive instruction with problem-solving tasks, and inductive instruction with structured input tasks on the acquisition of pragmatic competence. Sixty adult intermediate proficiency native speakers of Japanese were randomly assigned to one of four groups consisting of three treatment g...

This study involving 60 Japanese learners of English investigated the effects of various kinds of form-focused instruction on learners’ ability to comprehend and produce polite requests in English. Each treatment group received one of the following: (a) deductive instruction; (b) inductive instruction with problem-solving tasks; or (c) inductive instruction with structured input tasks. These ta...

We present a study that quantifies the effect of cold temperature on smartphone input performance, particularly on tapping tasks. Our results show that smartphone input performance decreases when completing tapping tasks in cold temperatures. We show that colder temperature is associated with lower throughput and less accurate performance when using the phone in both one-handed and two-handed o...