BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
By: Luca Colombo , Fabrizio Pittorino , Daniele Zambon and more
Potential Business Impact:
Trains AI using only simple math for speed.
Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy consumption. These advantages make them particularly well suited for deployment on resource-constrained devices. However, training BNNs via gradient-based optimization remains challenging due to the discrete nature of their variables. The dominant approach, quantization-aware training, circumvents this issue by employing surrogate gradients. Yet, this method requires maintaining latent full-precision parameters and performing the backward pass with floating-point arithmetic, thereby forfeiting the efficiency of binary operations during training. While alternative approaches based on local learning rules exist, they are unsuitable for global credit assignment and for back-propagating errors in multi-layer architectures. This paper introduces Binary Error Propagation (BEP), the first learning algorithm to establish a principled, discrete analog of the backpropagation chain rule. This mechanism enables error signals, represented as binary vectors, to be propagated backward through multiple layers of a neural network. BEP operates entirely on binary variables, with all forward and backward computations performed using only bitwise operations. Crucially, this makes BEP the first solution to enable end-to-end binary training for recurrent neural network architectures. We validate the effectiveness of BEP on both multi-layer perceptrons and recurrent neural networks, demonstrating gains of up to +6.89% and +10.57% in test accuracy, respectively. The proposed algorithm is released as an open-source repository.
Similar Papers
Scalable Equilibrium Propagation via Intermediate Error Signals for Deep Convolutional CRNNs
Machine Learning (CS)
Trains deep computer brains to learn much faster.
StochEP: Stochastic Equilibrium Propagation for Spiking Convergent Recurrent Neural Networks
Emerging Technologies
Trains brain-like computers to learn faster and better.
Bio-Inspired Artificial Neural Networks based on Predictive Coding
Machine Learning (Stat)
Brain learns without needing a final answer.