78 citations · 94 across the 10 of their papers we have counts for
12 papers
Teaching signal synchronization in deep neural networks with prospective neurons
Nicolas Zucchet, Qianqian Feng, Axel Laborieux +3
Working memory requires the brain to maintain information from the recent past to guide ongoing behavior. Neurons can contribute to this capacity by slowly integrating their inputs…
Theories of synaptic memory consolidation and intelligent plasticity for continual learning
Friedemann Zenke, Axel Laborieux
Humans and animals learn throughout life. Such continual learning is crucial for intelligence. In this chapter, we examine the pivotal role plasticity mechanisms with complex inter…
Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
Axel Laborieux, Friedemann Zenke
Equilibrium propagation (EP) is a compelling alternative to the backpropagation of error algorithm (BP) for computing gradients of neural networks on biological or analog neuromorp…
Implicit variance regularization in non-contrastive SSL
Manu Srinath Halvagal, Axel Laborieux, Friedemann Zenke
Non-contrastive SSL methods like BYOL and SimSiam rely on asymmetric predictor networks to avoid representational collapse without negative samples. Yet, how predictor networks fac…
Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations
Axel Laborieux, Friedemann Zenke
Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the training of deep neural networks with local learning rules. It thus provides a compelling fra…
Model of the Weak Reset Process in HfOx Resistive Memory for Deep Learning Frameworks
Atreya Majumdar, Marc Bocquet, Tifenn Hirtzlin +6
The implementation of current deep learning training algorithms is power-hungry, owing to data transfer between memory and logic units. Oxide-based RRAMs are outstanding candidates…
Synaptic metaplasticity in binarized neural networks
Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin +1
Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the…
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
Axel Laborieux, Maxence Ernoult, Benjamin Scellier +3
Equilibrium Propagation (EP) is a biologically-inspired counterpart of Backpropagation Through Time (BPTT) which, owing to its strong theoretical guarantees and the locality in spa…
Implementation of Ternary Weights with Resistive RAM Using a Single Sense Operation per Synapse
Axel Laborieux, Marc Bocquet, Tifenn Hirtzlin +5
The design of systems implementing low precision neural networks with emerging memories such as resistive random access memory (RRAM) is a significant lead for reducing the energy…
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
Axel Laborieux, Maxence Ernoult, Benjamin Scellier +3
Equilibrium Propagation (EP) is a biologically-inspired algorithm for convergent RNNs with a local learning rule that comes with strong theoretical guarantees. The parameter update…
Low Power In-Memory Implementation of Ternary Neural Networks with Resistive RAM-Based Synapse
Axel Laborieux, Marc Bocquet, Tifenn Hirtzlin +6
The design of systems implementing low precision neural networks with emerging memories such as resistive random access memory (RRAM) is a major lead for reducing the energy consum…
Synaptic Metaplasticity in Binarized Neural Networks
Axel Laborieux, Maxence Ernoult, Tifenn Hirtzlin +1
While deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previou…