Pruning deep neural networks is a widely used strategy to alleviate the
...
Reinforcement learning (RL) algorithms have proven transformative in a r...
Machine learning models are famously vulnerable to adversarial attacks: ...
Transformers are the type of neural networks that has revolutionised nat...
The ability of deep neural networks to generalise well even when they
in...
The recent success of neural networks in machine translation and other f...
Continual learning - learning new tasks in sequence while maintaining
pe...
Exploiting data invariances is crucial for efficient learning in both
ar...
Autoencoders are the simplest neural network for unsupervised learning, ...
Continual learning-the ability to learn many tasks in sequence-is critic...
Deep neural networks (DNNs) defy the classical bias-variance trade-off:
...
The advent of comprehensive synaptic wiring diagrams of large neural cir...
A recent series of theoretical works showed that the dynamics of neural
...
Teacher-student models provide a powerful framework in which the typical...
Direct Feedback Alignment (DFA) is emerging as an efficient and biologic...
Understanding the impact of data structure on learning in neural network...
The lack of crisp mathematical models that capture the structure of
real...
Deep neural networks achieve stellar generalisation even when they have
...
Deep neural networks achieve stellar generalisation on a variety of prob...