ZORB: A Derivative-Free Backpropagation Algorithm for Neural Networks

by   Varun Ranganathan, et al.

Gradient descent and backpropagation have enabled neural networks to achieve remarkable results in many real-world applications. Despite ongoing success, training a neural network with gradient descent can be a slow and strenuous affair. We present a simple yet faster training algorithm called Zeroth-Order Relaxed Backpropagation (ZORB). Instead of calculating gradients, ZORB uses the pseudoinverse of targets to backpropagate information. ZORB is designed to reduce the time required to train deep neural networks without penalizing performance. To illustrate the speed up, we trained a feed-forward neural network with 11 layers on MNIST and observed that ZORB converged 300 times faster than Adam while achieving a comparable error rate, without any hyperparameter tuning. We also broaden the scope of ZORB to convolutional neural networks, and apply it to subsamples of the CIFAR-10 dataset. Experiments on standard classification and regression benchmarks demonstrate ZORB's advantage over traditional backpropagation with Gradient Descent.



There are no comments yet.


page 1

page 2

page 3

page 4


A New Backpropagation Algorithm without Gradient Descent

The backpropagation algorithm, which had been originally introduced in t...

Memorized Sparse Backpropagation

Neural network learning is typically slow since backpropagation needs to...

Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations

Recent works have examined how deep neural networks, which can solve a v...

Backpropagation through nonlinear units for all-optical training of neural networks

Backpropagation through nonlinear neurons is an outstanding challenge to...

Low-memory stochastic backpropagation with multi-channel randomized trace estimation

Thanks to the combination of state-of-the-art accelerators and highly op...

Self learning robot using real-time neural networks

With the advancements in high volume, low precision computational techno...

Adapting Resilient Propagation for Deep Learning

The Resilient Propagation (Rprop) algorithm has been very popular for ba...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.