Source author record

Claudia Clopath

Claudia Clopath appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Neurons and Cognition Artificial Intelligence Machine Learning Biological Physics Neural and Evolutionary Computing nlin.AO

Catalog footprint

What is connected

8works

6topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Cortico-cerebellar modularity as an architectural inductive bias for efficient temporal learning

The cerebellum and cerebral cortex form tightly coupled circuits thought to support flexible and efficient temporal processing. How this interaction shapes cortical learning dynamics, and whether such heterogeneous modularity can benefit artificial systems, remains unclear. Here, we augment a recurrent neural network (RNN) with a cerebellar-inspired feedforward module and evaluate the resulting architecture on temporal tasks of varying difficulty. The cortico-cerebellar RNN (CB-RNN) learns faster and reaches higher maximum performance than parameter-matched fully recurrent baselines across a variety of regimes. Crucially, freezing the recurrent core after minimal training and delegating subsequent learning to the cerebellar module preserves superior learning efficiency, suggesting the cerebellar module is a primary driver of efficiency and that the cortical network can largely function as a fixed reservoir. Our results suggest that heterogeneous modular architectures can act as a powerful structural inductive bias in neural systems.

preprint2022arXiv

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 key issues discussed in this review include: synaptic plasticity, neural circuits, theory-experiment divide, and objective functions. We conclude with recommendations for both theoretical and experimental neuroscientists when designing new studies that could help bring clarity to these issues.

preprint2022arXiv

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. Surprisingly, the amount of forgetting does not increase with the dissimilarity between the learned tasks, but appears to be worst in an intermediate similarity regime. In this paper we theoretically analyse both a synthetic teacher-student framework and a real data setup to provide an explanation of this phenomenon that we name Maslow's hammer hypothesis. Our analysis reveals the presence of a trade-off between node activation and node re-use that results in worst forgetting in the intermediate regime. Using this understanding we reinterpret popular algorithmic interventions for catastrophic interference in terms of this trade-off, and identify the regimes in which they are most effective.

preprint2020arXiv

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. The basic MTR buffer comprises a cascade of sub-buffers that accumulate experiences at different timescales, enabling the agent to improve the trade-off between adaptation to new data and retention of old knowledge. We also combine the MTR framework with invariant risk minimization, with the idea of encouraging the agent to learn a policy that is robust across the various environments it encounters over time. The MTR methods are evaluated in three different continual learning settings on two continuous control tasks and, in many cases, show improvement over the baselines.

preprint2019arXiv

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. The same neural substrate may be used by the brain to produce different sequential behaviours. The way the brain learns and encodes such tasks remains unknown as current computational models do not typically use realistic biologically-plausible learning. Here, we propose a model where a spiking recurrent network of excitatory and inhibitory biophysical neurons drives a read-out layer: the dynamics of the driver recurrent network is trained to encode time which is then mapped through the read-out neurons to encode another dimension, such as space or a phase. Different spatiotemporal patterns can be learned and encoded through the synaptic weights to the read-out neurons that follow common Hebbian learning rules. We demonstrate that the model is able to learn spatiotemporal dynamics on time scales that are behaviourally relevant and we show that the learned sequences are robustly replayed during a regime of spontaneous activity.

preprint2017arXiv

Overcoming catastrophic forgetting in neural networks

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks which they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on the MNIST hand written digit dataset and by learning several Atari 2600 games sequentially.

preprint2016arXiv

Balanced activation in a simple embodied neural simulation

In recent years, there have been many computational simulations of spontaneous neural dynamics. Here, we explore a model of spontaneous neural dynamics and allow it to control a virtual agent moving in a simple environment. This setup generates interesting brain-environment feedback interactions that rapidly destabilize neural and behavioral dynamics and suggest the need for homeostatic mechanisms. We investigate roles for both local homeostatic plasticity (local inhibition adjusting over time to balance excitatory input) as well as macroscopic task negative activity (that compensates for task positive, sensory input) in regulating both neural activity and resulting behavior (trajectories through the environment). Our results suggest complementary functional roles for both local homeostatic plasticity and balanced activity across brain regions in maintaining neural and behavioral dynamics. These findings suggest important functional roles for homeostatic systems in maintaining neural and behavioral dynamics and suggest a novel functional role for frequently reported macroscopic task-negative patterns of activity (e.g., the default mode network).

preprint2015arXiv

Local inhibitory plasticity tunes global brain dynamics and allows the emergence of functional brain networks

Rich, spontaneous brain activity has been observed across a range of different temporal and spatial scales. These dynamics are thought to be important t for efficient neural functioning. Experimental evidence suggests that these neural dynamics are maintained across a variety of different cognitive states, in response to alterations of the environment and to changes in brain configuration (e.g., across individuals, development and in many neurological disorders). This suggests that the brain has evolved mechanisms to stabilize dynamics and maintain them across a range of situations. Here, we employ a local homeostatic inhibitory plasticity mechanism, balancing inhibitory and excitatory activity in a model of macroscopic brain activity based on white-matter structural connectivity. We demonstrate that the addition of homeostatic plasticity regulates network activity and allows for the emergence of rich, spontaneous dynamics across a range of brain configurations. Furthermore, the presence of homeostatic plasticity maximises the overlap between empirical and simulated patterns of functional connectivity. Therefore, this work presents a simple, local, biologically plausible inhibitory mechanism that allows stable dynamics to emerge in the brain and which facilitates the formation of functional connectivity networks.