Current literature demonstrates that Large Language Models (LLMs) are gr...
Large Language Models (LLMs) have demonstrated impressive performance on...
Early backdoor attacks against machine learning set off an arms race in
...
Data augmentation is used extensively to improve model generalisation.
H...
Neural networks are susceptible to adversarial examples-small input
pert...
Machine learning is vulnerable to adversarial manipulation. Previous
lit...
Bayesian Neural Networks (BNNs) offer a mathematically grounded framewor...
Federated Learning (FL) is a powerful technique for training a model on ...
Network Architecture Search (NAS) methods have recently gathered much
at...
The wide adaption of 3D point-cloud data in safety-critical applications...
Deep Graph Neural Networks (GNNs) show promising performance on a range ...
The high energy costs of neural network training and inference led to th...
It has always been difficult to balance the accuracy and performance of ...
We present the first differentiable Network Architecture Search (NAS) fo...
Convolutional Neural Networks (CNNs) are deployed in more and more
class...
Modern deep Convolutional Neural Networks (CNNs) are computationally
dem...
Recent research on reinforcement learning has shown that trained agents ...
Address translation and protection play important roles in today's
proce...
Deep convolutional neural networks (CNNs) are powerful tools for a wide ...
The Winograd or Cook-Toom class of algorithms help to reduce the overall...
Convolutional Neural Networks (CNNs) are widely used to solve classifica...
Deep Neural Networks (DNNs) have become a powerful tool for a wide range...
Making deep convolutional neural networks more accurate typically comes ...
As deep neural networks (DNNs) become widely used, pruned and quantised
...