Search Results for author:
Found 15 papers, 5 papers with code
Lifelong Reinforcement Learning via Neuromodulation
Navigating multiple tasks$\unicode{x2014}$for instance in succession as in continual or lifelong learning, or in distributions as in meta or multi-task learning$\unicode{x2014}$requires some notion of adaptation.
Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution
Neuroscience has long been an essential driver of progress in artificial intelligence (AI).
When Does Re-initialization Work?
However, when deployed alongside other carefully tuned regularization techniques, re-initialization methods offer little to no added benefit for generalization, although optimal generalization performance becomes less sensitive to the choice of learning rate and weight decay hyperparameters.
Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation
Continual learning - learning new tasks in sequence while maintaining performance on old tasks - remains particularly challenging for artificial neural networks.
A study on the plasticity of neural networks
One aim shared by multiple settings, such as continual learning or transfer learning, is to leverage previously acquired knowledge to converge faster on the current task.
Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece
We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them with the efficiency of gradient-based learning in recurrent neural networks.
Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective
We conduct ablation studies to disentangle the various effects normalisation has on the learning dynamics and show that is sufficient to modulate the parameter updates to recover most of the performance of spectral normalisation.
Continual Reinforcement Learning with Multi-Timescale Replay
In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent.
Cortical credit assignment by Hebbian, neuromodulatory and inhibitory plasticity
We propose that a combination of plasticity rules, 1) Hebbian, 2) acetylcholine-dependent and 3) noradrenaline-dependent excitatory plasticity, together with 4) inhibitory plasticity restoring E/I balance, effectively solves the credit assignment problem.
Neurons and Cognition Disordered Systems and Neural Networks
Learning spatiotemporal signals using a recurrent spiking network that discretizes time
Learning to produce spatiotemporal sequences is a common task that the brain has to solve.
Policy Consolidation for Continual Reinforcement Learning
We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments.
A High GOPs/Slice Time Series Classifier for Portable and Embedded Biomedical Applications
Such a trend in hardware design may not be efficient in applications where on-node computation is required and the focus is more on the area and power efficiency as in the case of portable and embedded biomedical devices.
Continual Reinforcement Learning with Complex Synapses
Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of previously acquired knowledge.
Overcoming catastrophic forgetting in neural networks
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
Ranked #3 on
Continual Learning
on F-CelebA (10 tasks)
An online Hebbian learning rule that performs Independent Component Analysis
Independent component analysis (ICA) is a powerful method to decouple signals.
