Zobrazeno 1 - 10
of 93
pro vyhledávání: '"RIDDLE, PATRICIA"'
We introduce PropNEAT, a fast backpropagation implementation of NEAT that uses a bidirectional mapping of the genome graph to a layer-based architecture that preserves the NEAT genomes whilst enabling efficient GPU backpropagation. We test PropNEAT o
Externí odkaz:
http://arxiv.org/abs/2411.03726
The distribution of streaming data often changes over time as conditions change, a phenomenon known as concept drift. Only a subset of previous experience, collected in similar conditions, is relevant to learning an accurate classifier for current da
Externí odkaz:
http://arxiv.org/abs/2408.09324
With the advancement in robotics, it is becoming increasingly common for large factories and warehouses to incorporate visual SLAM (vSLAM) enabled automated robots that operate closely next to humans. This makes any adversarial attacks on vSLAM compo
Externí odkaz:
http://arxiv.org/abs/2312.06991
A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability to predict the label via some method of generalisation. In the contex
Externí odkaz:
http://arxiv.org/abs/2311.12337
When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two methods fo
Externí odkaz:
http://arxiv.org/abs/2308.04711
We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to instill diverse
Externí odkaz:
http://arxiv.org/abs/2308.00946
In Simultaneous Localization and Mapping (SLAM), Loop Closure Detection (LCD) is essential to minimize drift when recognizing previously visited places. Visual Bag-of-Words (vBoW) has been an LCD algorithm of choice for many state-of-the-art SLAM sys
Externí odkaz:
http://arxiv.org/abs/2209.11894
Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has performed th
Externí odkaz:
http://arxiv.org/abs/2209.06923
Continual learning of a stream of tasks is an active area in deep neural networks. The main challenge investigated has been the phenomenon of catastrophic forgetting or interference of newly acquired knowledge with knowledge from previous tasks. Rece
Externí odkaz:
http://arxiv.org/abs/2208.06931
Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these models arrive
Externí odkaz:
http://arxiv.org/abs/2206.08486