Search Results for author:
Found 12 papers, 4 papers with code
BP(λ): Online Learning via Synthetic Gradients
Inspired by the accumulate $\mathrm{TD}(\lambda)$ in RL, we propose a fully online method for learning synthetic gradients which avoids the use of BPTT altogether: accumulate $BP(\lambda)$.
Single-phase deep learning in cortico-cortical networks
First, we demonstrate that our model can effectively backpropagate errors through multiple layers using a single-phase learning process.
Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation
Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values.
Cortico-cerebellar networks as decoupling neural interfaces
Recently, decoupled neural interfaces (DNIs) were introduced as a solution to the forward and feedback locking problems in deep networks.
Learning offline: memory replay in biological and artificial reinforcement learning
Learning to act in an environment to maximise rewards is among the brain's key functions.
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.
The role of Disentanglement in Generalisation
It is claimed that such representations should be able to capture the compositional structure of the world which can then be combined to produce novel representations.
Cortico-cerebellar networks as decoupled neural interfaces
Deep learning methods suffer from similar locking constraints both on the forward and backward phase.
HIPPOCAMPAL NEURONAL REPRESENTATIONS IN CONTINUAL LEARNING
The hippocampus has long been associated with spatial memory and goal-directed spatial navigation.
Dendritic cortical microcircuits approximate the backpropagation algorithm
Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience.
Dendritic error backpropagation in deep cortical microcircuits
Animal behaviour depends on learning to associate sensory stimuli with the desired motor command.
Cortical microcircuits as gated-recurrent neural networks
Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas.
