Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation

Abstract

We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction error is revealed). Although this algorithm computes the gradient of an objective function just like Backpropagation, it does not need a special computation or circuit for the second phase, where errors are implicitly propagated. Equilibrium Propagation shares similarities with Contrastive Hebbian Learning and Contrastive Divergence while solving the theoretical issues of both algorithms: our algorithm computes the gradient of a well defined objective function. Because the objective function is defined in terms of local perturbations, the second phase of Equilibrium Propagation corresponds to only nudging the prediction (fixed point, or stationary distribution) towards a configuration that reduces prediction error. In the case of a recurrent multi-layer supervised network, the output units are slightly nudged towards their target in the second phase, and the perturbation introduced at the output layer propagates backward in the hidden layers. We show that the signal 'back-propagated' during this second phase corresponds to the propagation of error derivatives and encodes the gradient of the objective function, when the synaptic update corresponds to a standard form of spike-timing dependent plasticity. This work makes it more plausible that a mechanism similar to Backpropagation could be implemented by brains, since leaky integrator neural computation performs both inference and error back-propagation in our model. The only local difference between the two phases is whether synaptic changes are allowed or not.

References in corpus (8)

• Towards Biologically Plausible Deep Learning
• Random feedback weights support learning in deep neural networks
• Why are deep nets reversible: A simple theory, with implications for training
• STDP as presynaptic activity times rate of change of postsynaptic activity
• Training recurrent networks online without backtracking
• Early Inference in Energy-Based Models Approximates Back-Propagation
• Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible
• Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity

Cited by in corpus (7)

• Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible
• Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity
• A Framework for Searching for General Artificial Intelligence
• How deep learning works --The geometry of deep learning
• Boltzmann machines for time-series
• Computational models of long term plasticity and memory
• Learning binary or real-valued time-series via spike-timing dependent plasticity