Zobrazeno 1 - 10
of 369
pro vyhledávání: '"Miller, Rob"'
Cooking recipes are one of the most readily available kinds of procedural text. They consist of natural language instructions that can be challenging to interpret. In this paper, we propose a model to identify relevant information from recipes and ge
Externí odkaz:
http://arxiv.org/abs/2401.12088
Whilst cooking is a very important human activity, there has been little consideration given to how we can formalize recipes for use in a reasoning framework. We address this need by proposing a graphical formalization that captures the comestibles (
Externí odkaz:
http://arxiv.org/abs/2306.09042
The human ability to repurpose objects and processes is universal, but it is not a well-understood aspect of human intelligence. Repurposing arises in everyday situations such as finding substitutes for missing ingredients when cooking, or for unavai
Externí odkaz:
http://arxiv.org/abs/2109.08425
Current radio frequency (RF) sensors at the Edge lack the computational resources to support practical, in-situ training for intelligent spectrum monitoring, and sensor data classification in general. We propose a solution via Deep Delay Loop Reservo
Externí odkaz:
http://arxiv.org/abs/2106.16087
We introduce a novel design for in-situ training of machine learning algorithms built into smart sensors, and illustrate distributed training scenarios using radio frequency (RF) spectrum sensors. Current RF sensors at the Edge lack the computational
Externí odkaz:
http://arxiv.org/abs/2104.00751
Publikováno v:
In International Journal of Approximate Reasoning February 2024 165
This paper investigates techniques for knowledge injection into word embeddings learned from large corpora of unannotated data. These representations are trained with word cooccurrence statistics and do not commonly exploit syntactic and semantic inf
Externí odkaz:
http://arxiv.org/abs/2010.01745
We show that compact fully connected (FC) deep learning networks trained to classify wireless protocols using a hierarchy of multiple denoising autoencoders (AEs) outperform reference FC networks trained in a typical way, i.e., with a stochastic grad
Externí odkaz:
http://arxiv.org/abs/1904.11874
Adversarial examples in machine learning for images are widely publicized and explored. Illustrations of misclassifications caused by slightly perturbed inputs are abundant and commonly known (e.g., a picture of panda imperceptibly perturbed to fool
Externí odkaz:
http://arxiv.org/abs/1902.08034
Autor:
Kokalj-Filipovic, Silvija, Miller, Rob
While research on adversarial examples in machine learning for images has been prolific, similar attacks on deep learning (DL) for radio frequency (RF) signals and their mitigation strategies are scarcely addressed in the published work, with only on
Externí odkaz:
http://arxiv.org/abs/1902.06044