Learning in the machine: The symmetries of the deep learning channel. (November 2017)

• Record Type: Journal Article
• Authors: Baldi, Pierre; Sadowski, Peter; Lu, Zhiqin
• Is Part Of: Neural networks. Volume 95(2017)
• Page Start: 110
• Page End: 133
• Publication Date: 2017-11
• Subjects: Neural networks -- Deep learning -- Backpropagation -- Local learning -- Learning channel -- Learning dynamics; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2017.08.008
• Languages: English
• ISSNs: 0893-6080

Abstract

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.