no code implementations • 22 Jan 2024 • Aissatou Diallo, Antonis Bikakis, Luke Dickens, Anthony Hunter, Rob Miller
We iteratively learn the graph structure and the parameters of a $\mathsf{GNN}$ encoding the texts (text-to-graph) one sequence at a time while providing the supervision by decoding the graph into text (graph-to-text) and comparing the generated text to the input.
no code implementations • 12 Jan 2024 • Aissatou Diallo, Antonis Bikakis, Luke Dickens, Anthony Hunter, Rob Miller
Decoding the core of procedural texts, exemplified by cooking recipes, is crucial for intelligent reasoning and instruction automation.
no code implementations • 15 Jun 2023 • Antonis Bikakis, Aissatou Diallo, Luke Dickens, Anthony Hunter, Rob Miller
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.
no code implementations • 17 Sep 2021 • Antonis Bikakis, Luke Dickens, Anthony Hunter, Rob Miller
Repurposing arises in everyday situations such as finding substitutes for missing ingredients when cooking, or for unavailable tools when doing DIY.
no code implementations • 1 Apr 2021 • Silvija Kokalj-Filipovic, Paul Toliver, William Johnson, Rob Miller
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.
no code implementations • 1 Apr 2021 • Silvija Kokalj-Filipovic, Paul Toliver, William Johnson, Rob Miller
We propose a solution via Deep Delay Loop Reservoir Computing (DLR), a processing architecture that supports general machine learning algorithms on compact mobile devices by leveraging delay-loop reservoir computing in combination with innovative electrooptical hardware.
no code implementations • 5 Oct 2020 • Diego Ramirez-Echavarria, Antonis Bikakis, Luke Dickens, Rob Miller, Andreas Vlachidis
This paper investigates techniques for knowledge injection into word embeddings learned from large corpora of unannotated data.
no code implementations • 13 Apr 2019 • Silvija Kokalj-Filipovic, Rob Miller, Joshua Morman
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 gradient based optimization of a given FC architecture.
no code implementations • 16 Feb 2019 • Silvija Kokalj-Filipovic, Rob Miller, Nicholas Chang, Chi Leung Lau
Adversarial examples in machine learning for images are widely publicized and explored.
no code implementations • 16 Feb 2019 • Silvija Kokalj-Filipovic, Rob Miller
It is not clear if the RF AdExs maintain their effects in the physical world, i. e., when AdExs are delivered over-the-air (OTA).
no code implementations • 20 Mar 2017 • Fabio Aurelio D'Asaro, Antonis Bikakis, Luke Dickens, Rob Miller
We also describe an ASP implementation of PEC and show the sense in which this is sound and complete.
no code implementations • 14 Jul 2014 • Irene-Anna Diakidoy, Antonis Kakas, Loizos Michael, Rob Miller
This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension.