4 citations · 11 across the 12 of their papers we have counts for
12 papers
Random Feedback Alignment Algorithms to train Neural Networks: Why do they Align?
Dominique Chu, Florian Bacho
Feedback alignment algorithms are an alternative to backpropagation to train neural networks, whereby some of the partial derivatives that are required to compute the gradient are…
Exploring Tradeoffs in Spiking Neural Networks
Florian Bacho, Dominique Chu
Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Deep Neural Networks for low-power computing. However, the effectiveness of SNNs is not solely…
Low-Variance Forward Gradients using Direct Feedback Alignment and Momentum
Florian Bacho, Dominique Chu
Supervised learning in deep neural networks is commonly performed using error backpropagation. However, the sequential propagation of errors during the backward pass limits its sca…
Programming molecular systems to emulate a learning spiking neuron
Jakub Fil, Neil Dalchau, Dominique Chu
Hebbian theory seeks to explain how the neurons in the brain adapt to stimuli, to enable learning. An interesting feature of Hebbian learning is that it is an unsupervised method a…
Integrate-and-Fire Neurons for Low-Powered Pattern Recognition
Florian Bacho, Dominique Chu
Embedded systems acquire information about the real world from sensors and process it to make decisions and/or for transmission. In some situations, the relationship between the da…
Constraints on Hebbian and STDP learned weights of a spiking neuron
Dominique Chu, Huy Le Nguyen
We analyse mathematically the constraints on weights resulting from Hebbian and STDP learning rules applied to a spiking neuron with weight normalisation. In the case of pure Hebbi…
A thermodynamically consistent chemical spiking neuron capable of autonomous Hebbian learning
Jakub Fil, Dominique Chu
We propose a fully autonomous, thermodynamically consistent set of chemical reactions that implements a spiking neuron. This chemical neuron is able to learn input patterns in a He…
Minimal spiking neuron for solving multi-label classification tasks
Jakub Fil, Dominique Chu
The Multi-Spike Tempotron (MST) is a powerful single spiking neuron model that can solve complex supervised classification tasks. While powerful, it is also internally complex, com…
A thermodynamically consistent model of finite state machines
Dominique Chu, Richard Spinney
Finite state machines (FSMs) are a theoretically and practically important model of computation. We propose a general, thermodynamically consistent model of FSMs and characterise t…
Information ratchets exploiting spatially structured information reservoirs
Richard E. Spinney, Mikhail Prokopenko, Dominique Chu
Information ratchets extract work from heat baths using low entropy information reservoirs. We find that the structure of the reservoirs affects both their performance and phase di…
The thermodynamics of quasi-deterministic digital computers
Dominique Chu
It is now well established that there is no lower bound for the energy dissipated during a computation. The relevance of the zero-energy limit is unclear, however, because it entai…
Performance limits and trade-offs in entropy-driven biochemical computers
Dominique Chu
The properties and fundamental limits of chemical computers have recently attracted significant interest as a model of computation, an unifying principle of cellular organisation a…