Learning in the machine: the symmetries of the deep learning channel

DOI10.1016/J.NEUNET.2017.08.008zbMATH Open1434.68497arXiv1712.08608OpenAlexW2963380291WikidataQ46132497 ScholiaQ46132497MaRDI QIDQ2179077FDOQ2179077

Pierre Baldi, Zhiqin Lu, Peter Sadowski

Publication date: 12 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Abstract: In a physical neural system, learning rules must be local both in space and time. In order for learning to occur, non-local information must be communicated to the deep synapses through a communication channel, the deep learning channel. We identify several possible architectures for this learning channel (Bidirectional, Conjoined, Twin, Distinct) and six symmetry challenges: 1) symmetry of architectures; 2) symmetry of weights; 3) symmetry of neurons; 4) symmetry of derivatives; 5) symmetry of processing; and 6) symmetry of learning rules. Random backpropagation (RBP) addresses the second and third symmetry, and some of its variations, such as skipped RBP (SRBP) address the first and the fourth symmetry. Here we address the last two desirable symmetries showing through simulations that they can be achieved and that the learning channel is particularly robust to symmetry variations. Specifically, random backpropagation and its variations can be performed with the same non-linear neurons used in the main input-output forward channel, and the connections in the learning channel can be adapted using the same algorithm used in the forward channel, removing the need for any specialized hardware in the learning channel. Finally, we provide mathematical results in simple cases showing that the learning equations in the forward and backward channels converge to fixed points, for almost any initial conditions. In symmetric architectures, if the weights in both channels are small at initialization, adaptation in both channels leads to weights that are essentially symmetric during and after learning. Biological connections are discussed.

Full work available at URL: https://arxiv.org/abs/1712.08608

zbMATH Keywords

deep learningneural networksbackpropagationlocal learninglearning dynamicslearning channel

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• A logical calculus of the ideas immanent in nervous activity
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• The dropout learning algorithm
• Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (2)

• Learning in the machine: random backpropagation and the deep learning channel
• Learning in the machine: to share or not to share?

Uses Software

• NEURON
• ImageNet
• AlexNet

This page was built for publication: Learning in the machine: the symmetries of the deep learning channel

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2179077)