no code implementations • 25 Apr 2021 • Mohammed Amer, Tomás Maul, Iman Yi Liao
In this work, we use a one-shot neural architecture search model to implicitly evaluate the performance of an intractable number of multipath neural networks.
no code implementations • 10 Dec 2019 • Mohammed Amer, Tomás Maul
Lifelong learning is a very important step toward realizing robust autonomous artificial agents.
no code implementations • 2 May 2019 • Mohammed Amer, Tomás Maul
Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains.
no code implementations • 29 Apr 2019 • Mohammed Amer, Tomás Maul
Based on an investigation of the different levels at which modularization techniques act, we attempt to provide a universal and systematic framework for theorists studying MNNs, also trying along the way to emphasise the strengths and weaknesses of different modularization approaches in order to highlight good practices for neural network practitioners.
no code implementations • 11 Feb 2019 • Mohammed Amer, Tomás Maul
Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter's invariance properties with equivariance through pose estimation.