Equilibrium Propagation with Continual Weight Updates

• URL: http://arxiv.org/abs/2005.04168v1
• Date: Wed, 29 Apr 2020 14:54:30 GMT
• Title: Equilibrium Propagation with Continual Weight Updates
• Authors: Maxence Ernoult, Julie Grollier, Damien Querlioz, Yoshua Bengio, Benjamin Scellier
• Abstract summary: We propose a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT) We prove theoretically that, provided the learning rates are sufficiently small, at each time step of the second phase the dynamics of neurons and synapses follow the gradients of the loss given by BPTT. These results bring EP a step closer to biology by better complying with hardware constraints while maintaining its intimate link with backpropagation.
• Score: 69.87491240509485
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input $x$ and associated target $y$, EP proceeds in two phases: in the first phase neurons evolve freely towards a first steady state; in the second phase output neurons are nudged towards $y$ until they reach a second steady state. However, in existing implementations of EP, the learning rule is not local in time: the weight update is performed after the dynamics of the second phase have converged and requires information of the first phase that is no longer available physically. In this work, we propose a version of EP named Continual Equilibrium Propagation (C-EP) where neuron and synapse dynamics occur simultaneously throughout the second phase, so that the weight update becomes local in time. Such a learning rule local both in space and time opens the possibility of an extremely energy efficient hardware implementation of EP. We prove theoretically that, provided the learning rates are sufficiently small, at each time step of the second phase the dynamics of neurons and synapses follow the gradients of the loss given by BPTT (Theorem 1). We demonstrate training with C-EP on MNIST and generalize C-EP to neural networks where neurons are connected by asymmetric connections. We show through experiments that the more the network updates follows the gradients of BPTT, the best it performs in terms of training. These results bring EP a step closer to biology by better complying with hardware constraints while maintaining its intimate link with backpropagation.

Related papers

• Contribute to balance, wire in accordance: Emergence of backpropagation from a simple, bio-plausible neuroplasticity rule [0.0]
  We introduce a novel neuroplasticity rule that offers a potential mechanism for implementing BP in the brain. We demonstrate mathematically that our learning rule precisely replicates BP in layered neural networks without any approximations.
  arXiv  Detail & Related papers  (2024-05-23T03:28:52Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons [15.147172044848798]
  We propose a simple energy based compartmental neuron model, termed dual propagation, in which each neuron is a dyad with two intrinsic states. The advantage of this method is that only a single inference phase is needed and that inference can be solved in layerwise closed-form. Experimentally we show on common computer vision datasets, including Imagenet32x32, that dual propagation performs equivalently to back-propagation.
  arXiv  Detail & Related papers  (2023-02-02T17:07:36Z)
• ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware [105.54048699217668]
  We show a competitive performance in accuracy with a clear advantage in the computational complexity for Event-Based Three-factor Local Plasticity (ETLP) We also show that when using local plasticity, threshold adaptation in spiking neurons and a recurrent topology are necessary to learntemporal patterns with a rich temporal structure.
  arXiv  Detail & Related papers  (2023-01-19T19:45:42Z)
• Sequence Learning Using Equilibrium Propagation [2.3361887733755897]
  Equilibrium Propagation (EP) is a powerful and more bio-plausible alternative to conventional learning frameworks such as backpropagation. We leverage recent developments in modern hopfield networks to further understand energy based models and develop solutions for complex sequence classification tasks using EP.
  arXiv  Detail & Related papers  (2022-09-14T20:01:22Z)
• Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations [5.279475826661643]
  Equilibrium propagation (EP) is an alternative to backpropagation (BP) that allows the training of deep neural networks with local learning rules. We show analytically that this extension naturally leads to exact gradients even for finite-amplitude teaching signals. We establish the first benchmark for EP on the ImageNet 32x32 dataset and show that it matches the performance of an equivalent network trained with BP.
  arXiv  Detail & Related papers  (2022-09-01T15:23:49Z)
• Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD [105.99301967452334]
  We show the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum) named as Spherical Motion Dynamics (SMD) We verify our assumptions and theoretical results on various computer vision tasks including ImageNet and MSCOCO with standard settings.
  arXiv  Detail & Related papers  (2020-06-15T14:16:33Z)
• Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation [69.87491240509485]
  Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. We propose a discrete-time formulation of EP which enables to simplify equations, speed up training and extend EP to CNNs. Our CNN model achieves the best performance ever reported on MNIST with EP.
  arXiv  Detail & Related papers  (2020-04-29T12:14:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.