Search Results for author:
Found 5 papers, 0 papers with code
Balancing Accuracy and Latency in Multipath Neural Networks
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.
Reducing Catastrophic Forgetting in Modular Neural Networks by Dynamic Information Balancing
Lifelong learning is a very important step toward realizing robust autonomous artificial agents.
Weight Map Layer for Noise and Adversarial Attack Robustness
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.
A Review of Modularization Techniques in Artificial Neural Networks
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.
Path Capsule Networks
Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter's invariance properties with equivariance through pose estimation.
